obsei MCP server

Q: How do I add obsei MCP to Claude Code?

Run `claude mcp add --env OBSEI_DB_KEY= obsei -- uvx obsei` in your terminal. Add `--scope user` to make it available in every project.

Q: How do I add obsei MCP to Cursor?

Open `~/.cursor/mcp.json` and add the server under `mcpServers`, using the Cursor config shown in the install section above.

✓ VerifiedCommit Nov 11, 2026

obsei/obsei · python · Apache-2.0

Analyze customer feedback by stripping PII before processing to find stable themes and provide cited evidence for AI agents.

Also known as obsei/obsei

stdio CRM & Marketing Security

Install GitHub ↗

Stars: 1,452
Tools: —
Downloads, 30 days: —
Latest version: 1.1.1
Last commit: Nov 11, 2026
License: Apache-2.0

What is obsei MCP?

obsei is an MCP server. Analyze customer feedback by stripping PII before processing to find stable themes and provide cited evidence for AI agents.

Summary generated from the project's README

About obsei MCP server

obsei provides a self-hosted, open source solution for analyzing customer feedback while maintaining privacy. It functions by redacting personally identifiable information before data reaches a large language model, allowing users to identify stable themes across various channels and languages. This tool is designed for developers and teams who need to process feedback from sources like Slack or the App Store without compromising sensitive user details.

Users can deploy this via Python 3.11 or newer using uvx or pip. The system requires a database key and a pseudonym salt, which can be managed through a .obsei/secrets.env file or environment variables like OBSEI_DB_KEY and OBSEI_PSEUDONYM_SALT. It supports various optional modules including local classifiers, multilingual embeddings, and name redaction. You can integrate it into AI environments like Claude Code, Gemini, or any MCP client using the obsei mcp command.

What you can do with it

1Redact sensitive user informationAn AI agent can process customer messages while ensuring all personal data is stripped before storage.
2Identify recurring customer themesA developer can use the system to find consistent patterns and topics within large sets of feedback.
3Query feedback with source citationsYou can ask an AI agent questions about customer sentiment and receive answers backed by specific evidence.
4Connect multiple feedback channelsThe tool allows for the easy addition of different data sources like Slack or App Store reviews.

Written from the project's README. Every use case is checked against a quote from it.

How to install obsei MCP

Formats verified 10 Nov 2026

Claude CodeCursorVS CodeClaude DesktopCodexGemini CLI

$ claude mcp add --env OBSEI_DB_KEY=<YOUR_OBSEI_DB_KEY> obsei -- uvx obsei

~/.cursor/mcp.json

{
  "mcpServers": {
    "obsei": {
      "command": "uvx",
      "args": [
        "obsei"
      ],
      "env": {
        "OBSEI_DB_KEY": "<YOUR_OBSEI_DB_KEY>"
      }
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "obsei": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "obsei"
      ],
      "env": {
        "OBSEI_DB_KEY": "<YOUR_OBSEI_DB_KEY>"
      }
    }
  }
}

claude_desktop_config.json

{
  "mcpServers": {
    "obsei": {
      "command": "uvx",
      "args": [
        "obsei"
      ],
      "env": {
        "OBSEI_DB_KEY": "<YOUR_OBSEI_DB_KEY>"
      }
    }
  }
}

~/.codex/config.toml

[mcp_servers.obsei]
command = "uvx"
args = ["obsei"]

[mcp_servers.obsei.env]
OBSEI_DB_KEY = "<YOUR_OBSEI_DB_KEY>"

~/.gemini/settings.json

{
  "mcpServers": {
    "obsei": {
      "command": "uvx",
      "args": [
        "obsei"
      ],
      "env": {
        "OBSEI_DB_KEY": "<YOUR_OBSEI_DB_KEY>"
      }
    }
  }
}

Set 3 environment variables before starting the server (below).Setup guides:Claude Code Cursor VS Code Claude Desktop

Configuration

OBSEI_DB_KEYSecret
The key that encrypts the database.
OBSEI_CONFIG
Path to obsei.yaml (default ./obsei.yaml).
OBSEI_DB
Path to the database, overriding store.path.

Name	Description
OBSEI_DB_KEY	The key that encrypts the database.	Secret
OBSEI_CONFIG	Path to obsei.yaml (default ./obsei.yaml).
OBSEI_DB	Path to the database, overriding store.path.

Automated checks

Ran Nov 12, 2026Full report →

100/100

Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work

Show this score in your README

Source repository linked and reachablePass
Open source license (OSI)Pass
Commit or release in the last yearPass
Package name not close to a popular packagePass
Remote endpoint uses HTTPSNot checked
Destructive tools are labelledNot checked
No hidden instructions to the modelPass
No critical advisory in the package or its dependenciesPass

README

View on GitHub

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.

Requires Python 3.11 or newer; on older Pythons, pip quietly installs the legacy 0.0.x, so keep the >=1.0 floor. 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]>=1.0"
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/

Docs: https://docs.obsei.com
Live demo: https://docs.obsei.com/demo/
Source: https://github.com/obsei/obsei
Container: ghcr.io/obsei/obsei:1.1.1

Read full README

obsei MCP questions

How do I add obsei MCP to Claude Code?

Run claude mcp add --env OBSEI_DB_KEY=<YOUR_OBSEI_DB_KEY> obsei -- uvx obsei in your terminal. Add --scope user to make it available in every project.

How do I add obsei MCP to Cursor?

Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.

How does obsei handle privacy?

It is a self-hosted alternative that strips PII (Personally Identifiable Information) before any LLM sees the data.

What are the Python version requirements?

The server requires Python 3.11 or newer to avoid installing legacy versions.

How can I use obsei with my AI tools?

You can install it via Claude Code, Gemini extensions, or use the MCP command in any MCP client.

Facts

Nov 12, 2026

Stars: 1,452
Downloads, 30 days: —
Latest version: 1.1.1
Last commit: Nov 11, 2026
License: Apache-2.0
Transport: stdio
Package: obsei

obsei ↗

Community publisher

Published by an independent maintainer.

Alternatives

Works with

Claude Code Cursor VS Code Claude Desktop Codex Gemini CLI Windsurf Devin

Badge for your README

Show your HostedMCP checks score. The badge links readers to install instructions for every client.

[![HostedMCP checks](https://api.hostedmcp.org/v1/badge/server/obsei/obsei.svg)](https://hostedmcp.org/servers/obsei/obsei/checks)

Maintainer?

Claim this listing to edit it and add the HostedMCP badge to your README.

Claim listing

Before you install

Servers run with the permissions you give them. Use the narrowest token or database role that does the job.

About obsei MCP server

What you can do with it

1Redact sensitive user informationAn AI agent can process customer messages while ensuring all personal data is stripped before storage.
2Identify recurring customer themesA developer can use the system to find consistent patterns and topics within large sets of feedback.
3Query feedback with source citationsYou can ask an AI agent questions about customer sentiment and receive answers backed by specific evidence.
4Connect multiple feedback channelsThe tool allows for the easy addition of different data sources like Slack or App Store reviews.

Written from the project's README. Every use case is checked against a quote from it.

{ "servers": { "obsei": { "type": "stdio", "command": "uvx", "args": [ "obsei" ], "env": { "OBSEI_DB_KEY": "<YOUR_OBSEI_DB_KEY>" } } } }

Configuration

OBSEI_DB_KEYSecret

The key that encrypts the database.

OBSEI_CONFIG

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

OBSEI_DB

Path to the database, overriding store.path.

Name	Description
OBSEI_DB_KEY	The key that encrypts the database.	Secret
OBSEI_CONFIG	Path to obsei.yaml (default ./obsei.yaml).
OBSEI_DB	Path to the database, overriding store.path.

uvx --from "obsei[recommended]>=1.0" obsei init # or: pip install "obsei[recommended]>=1.0" 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 MCP questions

How do I add obsei MCP to Claude Code?

Run claude mcp add --env OBSEI_DB_KEY=<YOUR_OBSEI_DB_KEY> obsei -- uvx obsei in your terminal. Add --scope user to make it available in every project.

How do I add obsei MCP to Cursor?

Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.

How does obsei handle privacy?

It is a self-hosted alternative that strips PII (Personally Identifiable Information) before any LLM sees the data.

What are the Python version requirements?

The server requires Python 3.11 or newer to avoid installing legacy versions.

How can I use obsei with my AI tools?

You can install it via Claude Code, Gemini extensions, or use the MCP command in any MCP client.

obsei MCP server

What is obsei MCP?

About obsei MCP server

What you can do with it

How to install obsei MCP

Install obsei MCP in Claude Code

Install obsei MCP in Cursor

Install obsei MCP in VS Code

Install obsei MCP in Claude Desktop

Install obsei MCP in Codex

Install obsei MCP in Gemini CLI

Configuration

Automated checks

README

obsei

obsei MCP questions

obsei MCP server

What is obsei MCP?

About obsei MCP server

What you can do with it

How to install obsei MCP

Install obsei MCP in Claude Code

Install obsei MCP in Cursor

Install obsei MCP in VS Code

Install obsei MCP in Claude Desktop

Install obsei MCP in Codex

Install obsei MCP in Gemini CLI

Configuration

Automated checks

README

obsei

obsei MCP questions