io.github.obsei/obsei·Security

obsei

Self-hosted customer feedback with PII stripped at ingest: search, stats and themes with citations.

Stars
1.4K
Version
1.0.0
License
Apache-2.0
Review
Passed
Source Website PyPI
Language
Python
Last commit
2h ago
Forks
179
Open issues
5
Registry update
Oct 15, 2026
customer-feedbackmcppii-redactionprivacyvoice-of-customer

Connect

pypi
Terminal
$claude mcp add obsei \  -e OBSEI_CONFIG=<obsei-config> \  -e OBSEI_DB=<obsei-db> \  -e OBSEI_DB_KEY=<obsei-db-key> \  -- uvx obsei==1.0.0

Environment variables

  • OBSEI_CONFIG

    Path to obsei.yaml (default ./obsei.yaml).

  • OBSEI_DB

    Path to the database, overriding store.path.

  • OBSEI_DB_KEYsecret

    The key that encrypts the database.

Security review

Review passed

Reviewed 2m ago.

metadata
scanned
packages
1 checked

No findings.

Tools

This server runs on your machine, so its tool list is not fetched before install — the README below describes what it offers.

README

obsei/obsei/packages/obsei/README.md

obsei

obsei

Voice of Customer without violating privacy. The self-hosted, open source alternative to Enterpret and Unwrap that strips PII before any LLM sees it. Collect feedback from every channel and language, redact personal data before it is stored, find stable themes, and let your AI agents answer questions with cited evidence.

1.0 is in pre-release and is not compatible with 0.0.x. Install it with the >=1.0.0rc1 specifier; a plain pip install obsei still gives 0.0.15.

uvx --from "obsei[recommended]>=1.0.0rc1" obsei init   # or: pip install "obsei[recommended]>=1.0.0rc1"
obsei try                                        # redacted, labelled preview; nothing stored
obsei add appstore                               # add sources and sinks without editing YAML
obsei add slack
obsei check
obsei run

obsei init writes the database key and pseudonym salt to .obsei/secrets.env (owner-only, git-ignored), which every command loads; on servers and in CI, set OBSEI_DB_KEY and OBSEI_PSEUDONYM_SALT or mount the file.

Optional extras: recommended (local and embeddings), local (in-process classifier), sql, google, apple, names (person-name redaction), embeddings (multilingual themes).

Use it from your AI tool: /plugin install obsei --marketplace obsei/obsei in Claude Code, gemini extensions install https://github.com/obsei/obsei, or uvx --from "obsei>=1.0.0rc1" obsei mcp in any MCP client. Codex, Copilot, VS Code, Cursor and others: https://docs.obsei.com/guides/ai-tools/

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

More in Security

VMware NSX Security

io.github.vmware-skills

VMware NSX security: DFW policies and exclusions, groups, tags, Traceflow, IDPS — 22 MCP tools.

NativeKeel

io.github.AlicanAkyol

React Native and Expo health check: upgrade blockers, store rules, crash risks, security findings

zn-gate

io.github.usezn

Local security layer for coding agents: secret redaction, prompt-injection checks and MCP proxy.

Firewall AIops

io.github.AIops-tools

Governed OPNsense + pfSense firewall ops: rules, NAT, VPN, DHCP, RCA. 35 tools.

guardvibe

io.github.goklab

Deterministic security layer your AI can't be. 594 rules, 39 tools, CLI + doctor + host audit.

MCP Safety Warden

io.github.gautamvarmadatla

MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.

Listing from the official MCP Registry · repository facts from GitHub, 2h ago.