mcpField
O
obsei

obsei

Local
obsei.comBusiness & Marketing1.4kUpdated 2w ago
RepositoryVisit website

About obsei

obsei is a self-hosted, open-source service for analyzing customer feedback while stripping PII before storage or LLM processing. It supports search, statistics, themes, and evidence-cited answers for teams collecting feedback across channels and languages.

Key features

  1. 01Collect feedback from multiple channels
  2. 02Strip PII before storage
  3. 03Search feedback and view statistics
  4. 04Identify stable themes
  5. 05Return answers with cited evidence

Use cases

  1. 01Aggregate feedback from different channels
  2. 02Remove personal data before LLM processing
  3. 03Analyze themes across languages
  4. 04Let AI agents answer with cited evidence

MCP support

obsei can run as `obsei mcp` for use in an MCP client, exposing its feedback analysis capabilities to AI tools.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "obsei-obsei": {
      "command": "uvx",
      "args": [
        "obsei"
      ],
      "env": {
        "OBSEI_CONFIG": "<OBSEI_CONFIG>",
        "OBSEI_DB": "<OBSEI_DB>",
        "OBSEI_DB_KEY": "<OBSEI_DB_KEY>"
      }
    }
  }
}
Run commanduvx obsei
Environment variables to set
OBSEI_CONFIGPath to obsei.yaml (default ./obsei.yaml).
OBSEI_DBPath to the database, overriding store.path.
OBSEI_DB_KEYSecretThe key that encrypts the database.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiobsei1.1.1

Tools

4

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
langanyNoISO 639-1 language code.
textanyNoCase-insensitive substring, any language.
limitintegerNo
sinceanyNoOnly feedback created at or after this.
themeanyNoTheme id from list_themes.
untilanyNoOnly feedback created before this.
intentanyNoClassifier label to match.
sourceanyNoSource type, e.g. appstore, playstore, csv.
sentimentanyNoClassifier label to match.
max_ratinganyNo
min_ratinganyNo

Details

From the project README

obsei

obsei

Know what customers are saying. Keep what they said private. 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 not compatible with 0.0.x; for the legacy toolkit, pip install "obsei<1".

uvx --from "obsei[recommended]>=1.0" obsei init   # or: pip install "obsei[recommended]"
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), notify (Telegram, Discord, email and more via Apprise).

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" obsei mcp in any MCP client. Codex, Copilot, VS Code, Cursor and others: https://docs.obsei.com/guides/ai-tools/

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.