com.socialseal/mcp·Marketing

SocialSeal

Measure how findable a brand is in TikTok, Instagram, YouTube and AI search, and what to post next.

Stars
0
Version
0.2.2
License
Other
Review
Passed
Language
Python
Last commit
7h ago
Forks
0
Open issues
0
Registry update
Oct 13, 2026
agent-skillsclaude-codecreator-contentdiscoverabilitymarketingmcpsocial-searchsocialsealugcvideo-dna

Connect

remote
Terminal
$claude mcp add --transport http mcp https://mcp.socialseal.co/mcp

Headers

Nothing to configure — it works as is.

Security review

Review passed

Reviewed 21m ago.

tools
120 tools scanned
metadata
scanned

No findings.

Tools

120
  • socialseal_get_scheduled_spending

    Read existing Monitor schedules, their per-run maximum, monthly exposure and standing approval. This does not publish or approve a schedule. Only a human may approve schedule terms and a monthly cap; changes to scope, schedule or price need fresh approval.

  • socialseal_resume_paid_operation

    Continue the same requested work after funding or human approval. Rechecks live workspace permission, the bound connector grant, the current quote and spending limits. Never submits a new arbitrary task or changes its inputs. Repeating this action cannot charge twice.

  • socialseal_get_paid_operation

    Read a preserved operation's status, quote, retained result and USD settlement receipt. Polling and retrieving prior results are free. Funding alone is not successful task completion.

  • socialseal_get_workspace_balance

    Read workspace prepaid USD funds, active holds, monthly UTC headroom and approval threshold. Subscription credits remain their own allowance and are never converted to a cash balance.

  • socialseal_start_visibility_check

    Receive one complete evidence-backed Visibility Check per user for a brand and market. Uses normal login, including consumer email. This is optional: a specific creator, video or export request should use its own action directly. Returns a durable operation; read candidate themes, continue with stored IDs, then retrieve the complete report. Failed or partial-only reports restore eligibility; reconnects reuse released work.

  • socialseal_continue_visibility_check

    Continue the same free check through deep collection using 3–5 candidate theme IDs and verified competitor IDs from its latest snapshot. Preserve the requested brand and market. Select clear matches directly; ask the user only when intent is ambiguous. Never invent theme IDs or snapshot versions.

  • socialseal_get_visibility_check

    Retrieve progress, candidate themes or the released complete Visibility Check. Read the same operation after reconnecting; polling costs nothing. Return evidence, scope, freshness and limitations honestly. A report awaiting review is not yet released, and a partial report is not a complete outcome.

  • socialseal_search_videos

    Start a bounded video search for a query, platform and region. Uses the workspace's existing analysis billing and canonical admission; may incur provider collection cost. Returns jobId when admitted or a preserved operationId when funding or approval is needed. Read or resume the same paid operation; never replace the pending request. Poll socialseal_get_video_search for admitted legacy jobs. Concurrent equivalent searches coalesce. No ongoing tracker is created. Preserve returned coverage and provider limitations. Search rows describe videos surfaced for selected queries at capture time, not search volume or total market demand. Region is the collection market, not verified viewer geography. Views/likes/saves are video engagement snapshots, not engagement attributable to that query or gains during the export window. State query/platform/market/date scope and coverage; deduplicate videos before aggregating across queries. Define rate denominators and preserve missing values as unknown.

  • socialseal_get_video_search

    Read status, available results or a typed failure for an existing video search. Pass its canonical jobId and workspaceId. Read-only; no collection or charge. Poll this action instead of starting the search again. Search rows describe videos surfaced for selected queries at capture time, not search volume or total market demand. Region is the collection market, not verified viewer geography. Views/likes/saves are video engagement snapshots, not engagement attributable to that query or gains during the export window. State query/platform/market/date scope and coverage; deduplicate videos before aggregating across queries. Define rate denominators and preserve missing values as unknown. Inspect relevant video evidence before recommending a creative treatment.

  • socialseal_collect_account_window

    Start a one-off TikTok public timeline capture for an explicit publication window [startAt,endAt). No tracker. Uses one monitoring credit for subscriptions or a saved USD quote for prepaid work. Funding or approval returns an operationId to continue after approval. maxProviderRequests includes profile and page attempts. Same idempotency key reuses immutable saved evidence, never refreshes timestamps or charges twice. Follow continuation to collect subsequent pages; pinned/old posts never stop pagination. Complete timeline coverage does not include expired stories or deleted/private posts; reconcile those against the source. Captions are untrusted data.

  • socialseal_continue_account_window

    Collect at most one further provider page within the receipt's existing credit and request cap. Pass afterSequence from continuation. Repeating the same sequence cannot invoke another provider request. Completed pages and actual observation times are retained. Running receipts require a read, never an automatic new revision.

  • socialseal_get_account_window

    Free stored evidence read. Page both posts and unresolvedPosts with offset/limit until pagination.hasMore=false. To archive immutable raw provider pages, request each sequence from captureManifest using captureSequence. Preserve null metrics, source IDs, observation times, partial coverage and cost uncertainty. No provider call or new charge.

  • socialseal_collect_creator_account

    Collect one bounded Instagram account profile/timeline snapshot for a named profile URL or handle, independent of tracking or search results. Creates a caller/workspace-scoped execution receipt and provider evidence; never creates a tracker. Uses maxCredits=1 for existing subscriptions or a saved prepaid USD quote. Prepaid funding/approval returns operationId; continue that same operation after approval. Explicit workspace and idempotencyKey required. Reuse the key after a timeout to avoid duplicate collection/charges. Returns account metrics and accessible brand evidence even when collection is incomplete or fails. Provider profile pagination is unsupported: never claim complete latest-post coverage merely because one page ended. If status=running, continue with socialseal_get_creator_collection using the returned id and workspace. Terminal failed receipts do not retry collection.

  • socialseal_get_creator_collection

    Read the status and evidence of one caller/workspace-scoped creator collection receipt. No provider call, charge or new tracker. Running receipts return continuation; complete and failed are terminal. Preserve partial metrics and brand evidence.

  • socialseal_get_creator_profile

    Read a supplied Instagram profile URL or handle directly, with account timeline posts (images, carousels and videos), publication dates, captions, available metrics, deterministic average views and engagement rates with formulas/denominators, freshness and coverage, plus accessible workspace brand context for host-owned brand-fit assessment. No resolver, skill or tracked-search setup prerequisite. Stored evidence only: no provider requests, credits, or persistent tracker. A fresh request returns FRESH_COLLECTION_REQUIRED and existing evidence; socialseal_collect_creator_account performs a separate bounded collection. Synchronous response; collection.continuation=null, no polling. Respect coverage.latestClaim; a partial timeline cannot establish the latest account posts. Missing brand evidence does not block metrics. Public views do not establish demographics or unique reach.

  • socialseal_get_creator_recent_posts

    Read a supplied Instagram profile URL or handle directly, with account timeline posts (images, carousels and videos), publication dates, captions, available metrics, deterministic average views and engagement rates with formulas/denominators, freshness and coverage, plus accessible workspace brand context for host-owned brand-fit assessment. No resolver, skill or tracked-search setup prerequisite. Stored evidence only: no provider requests, credits, or persistent tracker. A fresh request returns FRESH_COLLECTION_REQUIRED and existing evidence; socialseal_collect_creator_account performs a separate bounded collection. Synchronous response; collection.continuation=null, no polling. Respect coverage.latestClaim; a partial timeline cannot establish the latest account posts. Missing brand evidence does not block metrics. Public views do not establish demographics or unique reach.

  • socialseal_search_workspace_notes

    Find existing brand facts, constraints and decisions in authorized workspace notes. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_get_workspace_note

    Read an existing note by its returned ID. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_get_core_workspace_notes

    Read core context, building its stored cache from existing notes if absent. No provider collection or model cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_create_workspace_note

    Save a requested fact, preference, decision or constraint. No provider collection cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_update_workspace_note

    Replace the current workspace note with the supplied content as a new version, mark the previous version superseded and rebuild core context. Prior versions remain stored. Returns the new note and superseded note identifier. No provider collection cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_pin_workspace_note

    Change whether the specified note is included in core context. No provider collection cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_rebuild_core_workspace_notes

    Rebuild the core context from existing notes; does not collect social content. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_list_brands

    Retrieve existing brand context before asking the user for brand identifiers. Returns canonical brands and workspace roles. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_create_brand

    Create the explicitly requested brand identity and workspace role; no account monitoring or collection cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_list_brand_groups

    Read named sets of existing brands. These are not tracking groups. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_create_brand_group

    Create a named brand comparison set; no tracking or collection cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_update_brand_group

    Update a comparison set's name or description; no collection cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_delete_brand_group

    Delete the requested comparison set; no provider collection. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_add_brand_group_member

    Add an existing brand to the requested set; no tracking or collection cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_remove_brand_group_member

    Remove membership in the requested set; no provider collection. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_list_brand_aliases

    Read known attribution aliases for an accessible brand. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_create_brand_alias

    Attach a handle, hashtag or keyword attribution alias. A handle alias does not monitor the account; no collection cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_set_brand_alias_active

    Change the active state of one attribution alias; no collection cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_start_google_ai_search

    Start the specified Google AI queries. May incur provider collection cost under existing admission. Returns a numeric runId; poll socialseal_get_tool_status with kind=google_ai_run and read results after completion. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_list_google_ai_search_runs

    Read collected Google AI run status and progress, scoped to the requested run or tracking item. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_get_google_ai_search_results

    Read stored Google AI answers and citations, preserving the actual query and historical capture scope. Paginate offset/limit. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_create_tracking_group

    Create the requested single-platform tracking group; does not establish populated or fresh evidence. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_add_tracking_group_items

    Attach existing item IDs, or add search values with Topic assignments. Search adds use canonical Topic resolution; omitted Topics never create an unclassified active search. Returns item-level or typed activation outcomes. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_remove_tracking_group_item

    Remove only the requested group membership. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_update_tracking_group

    Update the requested group name, description or refresh schedule; scheduling can affect future collection. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_delete_tracking_group

    Delete the explicitly requested group; does not silently replace it or recollect evidence. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_refresh_tracking_group

    Queue collection for the existing group. May incur collection cost. Returns the existing refresh polling contract; no completion or freshness claim before status/evidence confirms it. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_get_tracking_group_refresh_status

    Read the existing group's collection queue state; does not start another refresh. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_list_tracking_groups

    Show existing authorized tracking groups across their configured platforms. Reads stored configuration without collection, refresh or setup; no new collection cost. Use the returned group ID and workspace for subsequent reads.

  • socialseal_get_tracking_group

    Read an existing tracking group's configuration by ID. Reads stored data; does not refresh evidence or create tracking. No new collection cost.

  • socialseal_get_tracking_group_completeness

    Compare expected memberships with stored items in the authorized tracking group, including missing/extra items, platform mismatches and optional stored refresh-job status. Omit expected_items to inspect current membership. Reads existing configuration/jobs only; no collection, refresh, mutation or new cost. Completeness does not establish fresh evidence. Reuse the workspace from the group lookup.

  • socialseal_list_tracking_group_items

    Read the monitored items in an existing tracking group, paginated by page and limit. Stored membership is not fresh search evidence. No collection or new collection cost; no setup prerequisite.

  • socialseal_list_tracking_items

    Read existing tracked items and their actual platform/market scope. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_get_tracking_item

    Read one existing tracked search, hashtag or account. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_find_tracking_item

    Find a target by exact type, value, platform and region, including inactive matches. Does not create tracking. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_list_workspace_topics

    Read active Topics with stable IDs, names and descriptions before assigning searches. No collection cost. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_track_account

    Create only the explicitly requested ongoing account commitment. May schedule provider refresh and incur collection cost under existing controls. Use creator reads for a one-off evaluation. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_track_search_or_hashtag

    Create the explicitly requested search/hashtag commitment. Active searches require Topic resolution: pass topicDefinitions and topicRefs, or omit them for automatic organisation. Unambiguous single-search automatic results preview and execute together; ambiguous results return TOPIC_INPUT_REQUIRED without activating. May schedule collection and incur cost under existing controls. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_preview_search_activation

    Return the exact Topics to create or reuse, per-search assignments, conflicts, credits and planFingerprint without activating. Use execute_search_activation with that fingerprint to commit. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_execute_search_activation

    Commit Topics, assignments and search activations atomically for a previewed plan. Requires planFingerprint and idempotencyKey. Duplicate retries return the original created or reused result. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_refresh_tracking_item

    Request fresh collection for an already monitored item. May incur collection cost; retain the returned job/status information and do not duplicate starts. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_update_tracking_item

    Update the requested item configuration; scheduling changes can affect future collection cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_delete_tracking_item

    Delete the requested tracking item. This changes ongoing monitoring; it is not needed for account metrics. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_get_video_evidence

    Read stored analysis for returned video identifiers. URLs are not accepted for polling; missing or pending evidence does not trigger provider work. Separate observed hooks/shots/transcripts from model interpretations. likelyReasonItRanks and similar explanations are hypotheses, not measured ranking causes or independent proof of effectiveness. Cite the source video and inspect whether its audience, topic and production context transfer to the requested brief. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_extract_video_assets

    Retrieve assets for stored video identifiers. Missing frame extraction or requested analysis may incur processing cost under existing controls. Returns per-item state and source links; poll analysis by returned ID, not URL. Separate observed hooks/shots/transcripts from model interpretations. likelyReasonItRanks and similar explanations are hypotheses, not measured ranking causes or independent proof of effectiveness. Cite the source video and inspect whether its audience, topic and production context transfer to the requested brief. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_analyse_public_video

    Queue analysis of a supplied public TikTok, Instagram or YouTube video URL without creating persistent tracking. Requires an authorized workspace; retrieve accessible workspace context before asking for an ID. May incur collection/analysis cost under existing backend admission controls; preserve required approval. Returns per-item status and identifiers; poll socialseal_get_tool_status with kind=video_analysis and the returned videoUid or platformVideoId, never the URL. Private/unavailable videos and provider errors are limitations, not a reason to set up tracking. Use returned evidence and timestamps; do not assume fresh collection or successful completion.

  • socialseal_list_source_clips

    Read existing source clips, rights metadata and available clip analysis; expiring media URLs are not permanent assets. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_prepare_source_clip_upload

    Create the requested source clip upload and return signed upload fields. Requires a separate byte upload and finalize action; no assembled-video output. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_finalize_source_clip_upload

    Finalize the requested upload only after bytes are uploaded and rights are attested. May trigger existing clip-analysis processing; preserve provider/admission failures. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_start_search_journey

    Start bounded keyword expansion for the specified subject/market. May incur collection/analysis cost under existing backend controls. Returns runId; poll socialseal_get_tool_status with kind=journey_run. Creates an execution, not an ongoing tracker. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_get_search_journey_run

    Read status and available results of the returned journey run; do not restart it to poll. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_get_blueprint

    Read the requested version and source evidence of a saved blueprint; missing evidence remains explicit. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_save_blueprint

    Save supplied evidence-backed blueprint content without provider collection. Do not fabricate evidence citations. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_generate_blueprint

    Generate a blueprint for the supplied scope or manual videos. May consume analysis credits; use previewOnly to inspect selection and retain existing admission/readiness controls. Read the returned opportunity/version with socialseal_get_blueprint; only a usable generated blueprint should feed socialseal_generate_brief. Draft means pending evidence and missing_data requires inspecting the stated gap. This is reference synthesis, not measured proof of creative effectiveness or a finished video. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_get_blueprint_shots

    Read existing shot panels and source references with expiring signed URLs; no new collection. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_refresh_blueprint_shots

    Regenerate reference panels for the selected blueprint. May incur processing cost under existing controls; this does not assemble a video. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_get_brief

    Read an existing brief version and evidence. Brand/strategy setup is not required to retrieve it. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_update_brief

    Save the requested creator-brief edits as a new version without modifying or deleting prior versions. Unspecified fields, evidence lineage and pinned context are preserved; supplied arrays replace that field in the new version (null arrays clear it). Supply briefId or opportunityKey. A stale base version is rejected. Reuse editId on retry; an unchanged retry can return NO_CHANGES before replaying the original result, so read the saved brief to verify its version. Without editId, retries may create additional versions. A successful write returns the saved brief, version and deduplication status. No collection cost. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_save_brief

    Save supplied brief content tied to a real blueprint version; no provider collection. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_generate_brief

    Create a video, creator, UGC or editor brief with hooks and shot direction. Use an existing blueprintId/version or a topic, competitor or tracking_group scope; retrievalPrompt refines scoped retrieval and cannot accompany blueprintId/version. Carry approved audience/product facts and constraints in brandContext; do not assume project documents are loaded. Read existing work with socialseal_get_brief, edit with socialseal_update_brief, and export with socialseal_export_brief before formatting as Word/PDF. May consume analysis credits under existing controls. Generated status does not establish factual accuracy, executable timing or creative quality; inspect the returned evidence and missing-data states. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_export_brief

    Export the requested brief version for handoff. No new provider collection; preserve returned artifact and evidence links. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_get_brief_readiness

    Check evidence readiness for creative brief generation or editing. This check does not gate unrelated reads, account metrics or URL analysis. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_start_brief_run

    Start the requested topic's brief execution, preserving backend readiness, budget and idempotency. May consume credits. Poll socialseal_get_brief_run with the returned runId; no social publishing or persistent account tracker. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_get_brief_run

    Read progress, result and failure evidence for an existing brief run. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_retry_brief_run

    Retry the existing run under backend context-fingerprint and idempotency checks. May consume credits. Poll socialseal_get_brief_run; do not silently force a full rerun. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_get_brief_outcomes

    Read weekly ranking outcomes only for posts actually linked to the specified brief; this sample is not total account reach. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_attach_brief_publication

    Attach an externally published video that this saved Brief produced. Requires the exact Brief ID, not a reference video. Reuses canonical video identity; duplicate conflicts preserve the original binding and baseline. URL resolution may incur collection cost under existing backend billing controls. Omitted trackingItemIds explicitly selects all workspace tracking; provide target IDs and region for scoped evidence. This does not publish content or prove causal uplift. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_list_search_journeys

    List existing journey identities and optionally their latest runs. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_get_search_journey

    Read a selected existing journey and optionally its latest execution. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_diagnose_search_journeys

    Read diagnostics for the existing journey scope without starting another run. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_list_keywords

    Read existing keyword records and their evidence/strategy associations. Listing keywords does not start searches. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_create_keyword

    Save the specified keyword and associations; does not create monitoring or collect provider data. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_create_keywords

    Save the specified keyword batch; does not create monitoring or collect provider data. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_update_keyword

    Update the requested keyword record and associations; no provider collection. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_update_keywords

    Apply the requested patch to the selected keyword IDs; no provider collection. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_delete_keyword

    Delete only the requested keyword record. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_sync_keywords_from_tracking

    Copy existing tracked keyword associations into the keyword registry; does not run provider collection. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_list_personas

    Read saved workspace personas. Personas are supplied strategy records, not inferred private audience demographics. Reads stored evidence/configuration; no provider collection or collection charge. Preserve returned timestamps, coverage, missing evidence and errors. Synchronous; no polling unless the result explicitly supplies continuation.

  • socialseal_create_persona

    Save the user's evidence-backed strategy persona; never fabricate private audience demographics. No provider collection. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_update_persona

    Apply requested changes to a saved strategy persona; no provider collection. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_retire_persona

    Mark the requested strategy persona inactive; no provider collection. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_reactivate_persona

    Reactivate the requested existing strategy persona; no provider collection. Changes only the requested workspace state. Backend authorization, validation and any quote/approval, budget and idempotency controls remain authoritative; tool selection does not authorize additional work.

  • socialseal_list_workspaces

    List workspaces visible to the authenticated SocialSeal user. List order and owner role do not identify the default; use defaultWorkspaceId/isDefaultWorkspace, or call socialseal_get_current_workspace before a write when the user did not name a workspace.

  • socialseal_get_current_workspace

    Get the current workspace before a workspace-scoped action when the user has not named one. Hosted MCP resolves the live active/default workspace, falling back to the sole accessible workspace; local MCP returns the workspace selected in environment/configuration.

  • socialseal_get_tool_status

    Read-only polling for a known SocialSeal async run, export, or group refresh. UUID auto ids are journey runs; numeric auto ids are Google AI runs. Both are workspace-scoped, as are google_ai_run, journey_run, explore_run, and video_analysis. Pass the workspaceId from the lookup that returned the run. MCP-host errors such as "No approval received" occur before SocialSeal executes this tool; never describe them as SocialSeal billing, workspace approval, or job-status errors.

  • socialseal_explore_preview_start

    Read the server-owned acquisition plan for an authorized workspace, anchor, market and language. Returns planFingerprint, estimated credits, capacity, source availability, blocking reasons and confirmationRequired. Does not create a lineage, queue a run or collect provider evidence. Pass the returned planFingerprint as previewFingerprint to socialseal_explore_start with the same scope. Ordinary plans need no additional user confirmation; request scope confirmation only when confirmationRequired is true.

  • socialseal_explore_start

    Start audience-demand research for the supplied anchor, market and language. Creates a research lineage and queues a collection run, which may consume credits and provider costs. First call socialseal_explore_preview_start; use its planFingerprint as previewFingerprint with the same scope, explicit workspace and retry key. Returns lineage/run identifiers and execution state; inspect the run for results. If the server requests scope confirmation, supply confirmedScopeFingerprint only after the user confirms that scope, reusing the same idempotencyKey.

  • socialseal_explore_list

    Read the canonical workspace Explore overview, including lineages, latest snapshots, recommendations, capabilities, and blocking reasons.

  • socialseal_explore_get

    Read one canonical Explore lineage, snapshot, run, selection, or compatible snapshot comparison. The response is returned without collapsing evidence, unavailable sources, or partial states.

  • socialseal_explore_refresh

    Queue a new demand-research run for an existing Explore lineage. May collect new provider evidence and consume credits. Requires the workspace, lineage and retry key. Returns run identifiers and execution state. Reuse the same idempotencyKey; supply confirmedScopeFingerprint only after requested scope confirmation.

  • socialseal_explore_select

    Persist an exact, user-confirmed Explore selection for a stated destination and intended use. No additional terms are inferred or added.

  • socialseal_explore_correct_interpretation

    Apply one canonical interpretation correction with stable retry identity and the exact labels and memberships supplied by the caller.

  • socialseal_explore_preview_activation

    Request the server-owned activation plan for an immutable Explore selection without activating it.

  • socialseal_explore_activate_searches

    Activate the selected Explore searches as Monitor tracking using the supplied preview plan and complete bindings. Creates, extends or reuses Monitor scope, reconciles workspace defaults and may queue baseline collection under existing credit controls. Returns activation status, identifiers and blocking reasons; collected results are available later. Requires an explicit workspace and idempotencyKey; supply confirmedScopeFingerprint only after requested scope confirmation.

  • socialseal_explore_handoff

    Prepare a server-issued Explore continuation for the selected destination. A handoff is not action acceptance and carries no client-inferred payload.

  • socialseal_explore_create_deliverable

    Create a shareable JSON report from an existing Explore selection, including its saved search terms, interpretation, evidence and limitations. Saves an immutable report and creates an external share link valid for 30 days. Requires an explicit workspace, selection and idempotencyKey. Retries reuse the report but issue a fresh share link.

  • socialseal_export_tracking_data

    Export legacy time-window tracking data for the authenticated SocialSeal user. Always reuse the workspaceId from the lookup that returned the selected group or tracking item; numeric IDs are not sufficient workspace context. Fulfilled as an export artifact: returns download_url plus a read_token for in-session paginated reads with socialseal_read_export_chunk when the URL cannot be fetched. For ranked discoverability, use socialseal_export_report with reportType search_results_enriched.

  • socialseal_export_report

    Export a SocialSeal report. Use reportType search_results_enriched, format csv and payload.groupIds for ranked search results; reuse the workspace from the group lookup. Poll the returned export ID while pending, then fetch download_url or page socialseal_read_export_chunk with read_token until has_more is false. Report partial coverage if retrieval stops early. Search rows describe videos surfaced for selected queries at capture time, not search volume or total market demand. Region is the collection market, not verified viewer geography. Views/likes/saves are video engagement snapshots, not engagement attributable to that query or gains during the export window. State query/platform/market/date scope and coverage; deduplicate videos before aggregating across queries. Define rate denominators and preserve missing values as unknown. Inspect relevant video evidence before recommending a creative treatment.

  • socialseal_read_export_chunk

    Read rows of a previously generated SocialSeal export artifact in-session, paginated as JSON. Use this when the export tool returns a download_url you cannot fetch (e.g. sandbox egress limits or web_fetch cannot render a CSV attachment). Pass the short download token (the `t` query param from download_url) plus offset and limit. Each call returns { export_history_id, headers, rows, offset, limit, next_offset, total, has_more }. Rows are packed by serialized char budget (not a fixed row count), so `limit` reflects the actual number of rows returned and may be smaller than requested. To page: if has_more is true, call again with offset = next_offset. Repeat until has_more is false. Prefer limit=200 as the max-rows cap. The data stays inside the MCP tool channel, so no URL fetch is required.

  • socialseal_discover_concepts

    Discover the canonical SocialSeal concept registry: metric concepts (discoverability, visibility, share of voice, reach, ranking, sentiment) and the domain glossary, with definitions, distinctions, required dimensions, evidence requirements, and input-only aliases.

  • socialseal_discover_capabilities

    Look up released capability metadata. Optional reference; this does not gate execution or authorize work.

  • socialseal_list_skills

    Discover optional task-specific SocialSeal guidance after identifying the requested work. For a content calendar or posting schedule, select socialseal-social-plan-builder; for video/editor/UGC briefs, select socialseal-creator-briefing. Loading guidance does not execute generation tools. Skills are not prerequisites for basic operations. Returns each skill's name and frontmatter description (so you can route without reading every SKILL.md), file paths, shared references, the install command, and the archive download info.

  • socialseal_read_skill

    Read the full instructions for one SocialSeal skill. Provide skill (and optional file, defaulting to SKILL.md) to read within skills/<skill>/, or provide path to read a repo-relative file under skills/, references/, docs/, templates/, or examples/.

  • socialseal_get_skills_archive

    Return download URLs for the full SocialSeal agent-skills repository (zip/tarball) plus the install command, so the agent or user can download every skill at once.

SocialSeal Agent Skills

skills.sh

Open-source Agent Skills for SocialSeal workflows: social-search strategy across TikTok, Instagram, Xiaohongshu/RedNote, Douyin, YouTube Shorts, and other social platforms; evidence-grounded video/carousel production; creator/UGC planning; and discoverability measurement.

Install

ChatGPT and Codex (recommended)

Install SocialSeal — Social Search & Video from the Plugins Directory, connect to SocialSeal when prompted, and start a new task. The plugin bundles the SocialSeal skills and its hosted remote MCP server at https://mcp.socialseal.co/mcp, so users do not need to add a separate custom connector or install Node.js.

Search for SocialSeal by name, or through jobs such as social search, social video, short-form video, TikTok SEO, Instagram Reels, Xiaohongshu/RedNote, Douyin, creator content, UGC, content strategy, competitor analysis, or discoverability tracking.

The public ChatGPT/Codex listing must be submitted and published as a With MCP plugin in the OpenAI plugin submission portal. Updating this repository does not by itself replace the reviewed public listing or its MCP metadata snapshot. See the ChatGPT and Codex submission checklist.

Codex local and repository development

This repository includes the native .codex-plugin/plugin.json manifest and a bundled .mcp.json connection to the hosted SocialSeal MCP server. Add the repository as a marketplace source, install socialseal-agent-skills, then start a new Codex session so the new skills and tools are loaded:

codex plugin marketplace add OpenSealAI/agent-skills
codex plugin add socialseal-agent-skills@socialseal-skills

If authentication is required, follow the connection prompt and sign in to SocialSeal. For local testing in ChatGPT Chat or Work, enable Developer mode, register https://mcp.socialseal.co/mcp in the Plugins page, and use the generated registered connection when packaging a local .app.json mapping.

Claude Cowork and non-technical users

Use the hosted SocialSeal remote MCP connector for live tools, then install this plugin for skills. This is the default path for Cowork because it does not require local Node.js, npx, terminal commands, or local config files.

  1. Open Customize -> Connectors.
  2. Click + -> Add custom connector.
  3. Fill in Name: socialseal and Remote MCP server URL: https://mcp.socialseal.co/mcp.
  4. Click Add/Connect and sign in to SocialSeal.
  5. Open the Cowork tab, then open Customize in the left sidebar.
  6. Go to the Plugins tab. Under Personal plugins, click + -> Add marketplace -> Add from a repository.
  7. Enter OpenSealAI/agent-skills and confirm.
  8. Click Install on socialseal-agent-skills.

Skills then appear via / or the + button. If tools are not initially visible, use the host's available tool search/discovery facilities first. A missing initial tool list does not establish that the connector is disconnected. Return to Customize -> Connectors, confirm socialseal (https://mcp.socialseal.co/mcp) is connected, and retry. If the connector is not available, use file mode with SocialSeal CSV/JSON exports.

For a large content plan or production request, explicitly start with socialseal-orchestrator if Claude does not select it automatically. The orchestrator will check brand utility, demand evidence, benchmarks, asset choices, prototypes, and delivery state before routing into downstream skills.

Claude Code

Install the skills plugin:

/plugin marketplace add OpenSealAI/agent-skills
/plugin install socialseal-agent-skills@socialseal-skills

The plugin bundles the hosted SocialSeal connector. Run /mcp, select socialseal, and sign in to SocialSeal in the browser window that opens.

Cursor and Grok Bot

The Cursor-format package at .cursor-plugin/plugin.json connects to the hosted SocialSeal MCP server and includes all 23 skills through Cursor's default discovery of skills/*/SKILL.md. Routine social-search, profile, and post requests use the live tools directly; they do not require a tracking group or the production skills. Follow the tools' current schemas, account permissions, collection quotes, and approval requirements. A SocialSeal account is required; available operations depend on that account's entitlements.

For local Cursor development, load this checkout with agent --plugin-dir /absolute/path/to/agent-skills, then complete the SocialSeal browser sign-in when prompted. The package references .mcp.json; it does not require Node.js, an API key, or a separate local MCP server.

Example requests:

  • "Research social-search results for my brand and market, with source links."
  • "Get this creator's recent posts and explain which engagement metrics are available."
  • "Evaluate this creator for a brand partnership using recent posts and the brand evidence I provide."

Marketplace review and Grok Bot compatibility are pending. This repository is not proof of a published Grok listing. Once SocialSeal is available in Grok Bot's Plugins catalogue, add it, complete the SocialSeal browser authorization, and confirm it appears under Installed. See the official Grok plugin connection guide. A custom MCP connection is an assisted setup and does not travel with a shared Grok bot template; recipients must connect their own SocialSeal account.

skills.sh (skills only)

npx skills add OpenSealAI/agent-skills

The Claude plugin manifest lives at .claude-plugin/plugin.json; the root .mcp.json declares the hosted HTTP MCP server, which Cowork and Claude Code both use. The native ChatGPT/Codex package instead lives at .codex-plugin/plugin.json and bundles the hosted MCP connection through .mcp.json.

What this helps agents do

  • Set up SocialSeal workspace scope and measurement surfaces.
  • Design tracking groups, keyword sets, markets, platforms, and competitor scopes.
  • Analyze discoverability gaps and competitor/content patterns.
  • Shortlist creator-shop partners by search authority, monitor bilingual (local-vs-English) demand, and route resources to early demand signals.
  • Run the SocialSeal production engine: identify and analyze reference videos (Video DNA), compile best-practices blueprints, generate briefs from blueprints, and prepare source clips and editor handoffs.
  • Build social plans, creator briefs, video concepts, asset plans, and editor handoffs.
  • Read out posted content and campaign performance, track discoverability, and plan next actions.

What this does not do

Asset Studio video generation and CapCut/FCPXML export skills have retired. Use brief exports and rights-cleared source clips for an editor handoff; SocialSeal does not assemble or render that video.

This repo does not automate posting, scheduling, inbox/comment/DM management, account growth tactics, paid media buying, or day-to-day social account operations.

Integration modes

  • MCP mode (preferred): use the hosted SocialSeal connector, or the local developer fallback @socialseal/mcp-server. Select the named operation from the host's tool catalogue and pass its typed arguments directly.
  • File mode: use user-provided SocialSeal exports.

Always inspect the live registry/schema before mutating calls. See references/mcp-and-cli-usage.md and references/production-pipeline.md. For how to cite evidence in human-readable terms and how confident to be about it, see references/socialseal-data-contract.md and references/evidence-and-confidence.md; for the strategy concepts the skills assume, see references/strategy-foundations.md.

The prepared 0.8.2 bundle requires the coordinated MCP release with named tracking-group completeness. Deploy that reviewed catalogue before refreshing installed bundles, then verify each supported host. Repository publication and installed host versions are separate; report an unavailable operation precisely.

Skill taxonomy

Orchestration

  • socialseal-orchestrator (coordinates explicitly requested multi-stage creative production)
  • socialseal-strategy-readiness (diagnoses strategy + setup readiness and guides the user to define what is missing)

Strategy

  • socialseal-workspace-setup
  • socialseal-tracking-group-design
  • socialseal-opportunity-analysis
  • socialseal-competitor-content-analysis
  • socialseal-creator-evaluation (supplied creator, recent-post metrics, and grounded brand fit)
  • socialseal-creator-discovery (shortlist creator-shop partners by market, language, and destination/topic authority from search evidence)
  • socialseal-bilingual-demand-monitoring (map the local-language vs English search-demand split and catch micro-trends early)
  • socialseal-predictive-demand-routing (source early demand signals to back resource allocation and fast-track activity/tour onboarding)
  • socialseal-social-plan-builder

Production

These follow the SocialSeal vNext engine: opportunity -> reference videos -> blueprint -> brief -> source-clip/editor handoff, joined by a single opportunityKey. See references/production-pipeline.md.

  • socialseal-video-concepting
  • socialseal-reference-video-analysis
  • socialseal-blueprint-builder
  • socialseal-creator-briefing
  • socialseal-asset-planning
  • socialseal-generation-prompts
  • socialseal-carousel-production (evidence, visual direction, asset selection, prototype approval, rendered slides, and post-ready QA for carousels)

For multi-stage creative work, the skills use explicit foundation, demand, benchmark, asset, prototype, and final-QA gates. See references/creative-production-gates.md.

Measurement

  • socialseal-performance-readout
  • socialseal-discoverability-tracking
  • socialseal-content-adjustment-recommendations
  • socialseal-management-reporting
  • socialseal-follow-up-planning

Content principle

SocialSeal primarily supports UGC and creator content, not advertising. These skills use two content lenses:

  • Aspirational: creates emotion or mood.
  • Utility/practical: teaches useful information and gives the viewer an unlock, relief, accomplishment, or confidence.

Distribution

This repository is structured for:

  • Agent Skills / skills.sh: skills/<skill-name>/SKILL.md
  • ChatGPT/Codex plugin: .codex-plugin/plugin.json, .mcp.json, and skills/
  • Cursor-format package: .cursor-plugin/plugin.json, .mcp.json, and all 23 skills; marketplace review and Grok compatibility pending
  • Claude Code plugin marketplace: .claude-plugin/plugin.json plus direct skills/ children
  • Hermes project usage through the same SKILL.md files

License

MIT

From the server's repository — third-party content, read it before running anything it suggests.

More in Marketing

Listing from the official MCP Registry · repository facts from GitHub, just now.