- Language
- JavaScript
- Last commit
- 37m ago
- Forks
- 0
- Open issues
- 1
- Registry update
- Oct 15, 2026
Connect
remote$claude mcp add --transport http upstream https://upstream.toolweather.workers.dev/mcp \ --header "X-API-Key: <x-api-key>"
Headers
X-API-KeysecretOptional free key (POST https://upstream.toolweather.workers.dev/v1/keys) for 500 free calls/day; 50/day without one
Security review
Partly reviewedReviewed 24m ago. Tool definitions changed on Oct 15, 2026.
- tools
- 5 tools scanned
- metadata
- scanned
- mediumReviewTool definitions changed after an earlier review
A server that changes its tool descriptions after being approved ("rug pull") can slip new instructions to agents. Re-check what changed before trusting it.
changed 2026-10-15
Tools
5check_api_status
Check if an AI or developer API provider (OpenAI, Anthropic, Gemini, Mistral, Groq, GitHub, Stripe, Cloudflare, Vercel, Supabase, Twilio... ~40 total) is up, degraded or down right now. Use BEFORE calling a provider's API, or right after you get 5xx/429/timeout errors, to decide whether to retry, wait or switch to a fallback. Returns a one-line summary first, then verdict, recommended_action, open incidents, affected components, checked_at and freshness (checked every ~4 min). Example: {"provider":"openai"}. Free within the daily quota, then $0.003 via x402. Alias: get_status.
check_model_deprecation
Check if an LLM model id is active, deprecated or retired, its shutdown date, and the recommended replacement, from the provider's own deprecation page (OpenAI, Anthropic, Google, etc.). Use before hard-coding or calling a model, or when a model call fails with "model not found / deprecated". Returns summary first, then verdict, recommended_action (keep_using | plan_migration | switch_now | verify_with_provider), replacement, shutdown_date, evidence rows and freshness. Example: {"model":"gpt-4-0613"}. Free within the daily quota, then $0.003 via x402. Alias: get_model (param "id").
list_recent_api_changes
List recent breaking or notable changes across AI and developer APIs: outages and recoveries, deprecation-page edits, model retirements and pricing-page edits. Use to answer "did anything change that could break my integration?" or to explain sudden errors. Returns summary first, then the change list with timestamps and source links. Example: {"provider":"anthropic","kind":"model_retirement"}. Free within the daily quota, then $0.01 via x402. Alias: get_changes.
list_providers
List the ~40 AI and developer API providers Upstream tracks with their current state (operational/degraded/outage) and checked_at. Use to find the right provider id for check_api_status, or for a quick all-providers health overview. Free.
get_digest
Daily digest (free) of AI/dev API incidents, model deprecations/retirements, pricing-page changes and breaking MCP server changes. Use for a once-a-day catch-up instead of polling. Example: {} for the latest, or {"date":"2026-10-14"}.
Upstream
Part of the Toolweather suite. The same tools are also available on the Toolweather MCP at https://toolweather.toolweather.workers.dev/mcp (proxied here). This Worker remains the source of truth for REST, digests and x402 payments.
Live status and breaking-change feed for the AI and developer APIs agents depend on: outages, model deprecations and retirements, pricing-page changes. ~40 providers.
- Site: https://upstream-api.pages.dev
- API: https://upstream.toolweather.workers.dev (llms.txt, OpenAPI)
- MCP:
https://upstream.toolweather.workers.dev/mcp
Free tier
500 calls/day with a free key (POST /v1/keys), 50/day anonymous, 1 free change-alert webhook. Above that, pay per call with x402 (Base mainnet, real USDC): /status/:provider $0.003, /model/:id $0.003, /changes $0.01, extra watch $0.05/30 days.
Stack
Cloudflare Worker (free plan) + D1, Hono, @x402/hono with the PayAI facilitator (Base mainnet). Pay-to address, network and facilitator are env vars in wrangler.toml, so switching to mainnet is a config change.
Cron every minute: a quarter of the providers per run (each provider ~every 4 min), one tracked docs page every 5 min.
From the server's repository — third-party content, read it before running anything it suggests.
More in Dev tools
CGIS Code Graph
io.github.zaebee
Code graph for AI agents: impact analysis and call tracing for Python, TypeScript and Go.
contextforge-mcp
io.github.alfredoizdev
Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.
misakanet
io.github.Ikalus1988
Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
jCodemunch MCP
io.github.jgravelle
Token-efficient code exploration via tree-sitter AST parsing. 70+ languages, 86-99% token savings.
Trusty Squire
ai.trustysquire
Provision, ship, and pay from your coding agent — keys and cards never leave the vault.
Kurlo
dev.kurlo
Run, write and test the API requests saved in a Kurlo workspace, the open source API client.
Listing from the official MCP Registry · repository facts from GitHub, 27m ago.