Skip to content
Back to search

mcp-maigret

MCP server for maigret, a powerful OSINT tool that collects user account information from various public sources.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/w0h1v/mcp-maigret with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/w0h1v/mcp-maigret'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/w0h1v--mcp-maigret/badge.svg)](/listings/w0h1v--mcp-maigret)

HTML

<a href="/listings/w0h1v--mcp-maigret"><img src="/api/listings/w0h1v--mcp-maigret/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Installing via Smithery

To install Maigret for Claude Desktop automatically via [Smithery](https://smithery.ai/server/mcp-maigret):

npx -y @smithery/cli install mcp-maigret --client claude

Installing Manually

1. Install Docker: - macOS: Install [Docker Desktop](https://www.docker.com/products/docker-desktop) - Linux: Follow the [Docker Engine installation guide](https://docs.docker.com/engine/install/)

2. Install the server globally via npm:

npm install -g mcp-maigret

3. Create a reports directory:

mkdir -p /path/to/reports/directory

4. Add to your Claude Desktop configuration file:

{
  "mcpServers": {
    "maigret": {
      "command": "mcp-maigret",
      "env": {
        "MAIGRET_REPORTS_DIR": "/path/to/reports/directory"
      }
    }
  }
}

Configuration file location: - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` - Windows: `%APPDATA%\Claude\claude_desktop_config.json`

5. Restart Claude Desktop

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 192 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center">
  2. <picture>
  3. <source media="(prefers-color-scheme: dark)" srcset="docs/assets/banner-dark.svg">
  4. <img alt="mcp-maigret: OSINT username search for AI agents" src="docs/assets/banner-light.svg" width="100%">
  5. </picture>
  6. </p>
  7. <p align="center">
  8. <a href="https://www.npmjs.com/package/mcp-maigret"><img alt="npm version" src="https://img.shields.io/npm/v/mcp-maigret"></a>
  9. <a href="https://github.com/w0h1v/mcp-maigret/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/w0h1v/mcp-maigret/actions/workflows/ci.yml/badge.svg"></a>
  10. <a href="LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/license-MIT-blue"></a>
  11. <img alt="Node 18 or newer" src="https://img.shields.io/badge/node-%E2%89%A518-339933">
  12. <a href="https://modelcontextprotocol.io"><img alt="MCP server" src="https://img.shields.io/badge/MCP-server-7c3aed"></a>
  13. </p>
  14. <p align="center">
  15. <a href="#quickstart">Quickstart</a> ·
  16. <a href="#tools">Tools</a> ·
  17. <a href="#output-formats">Formats</a> ·
  18. <a href="#security">Security</a> ·
  19. <a href="#troubleshooting">Troubleshooting</a> ·
  20. <a href="https://w0h1v.github.io/mcp-maigret/">Docs</a>
  21. </p>
  22. **mcp-maigret** is an [MCP](https://modelcontextprotocol.io) server that lets AI agents run [maigret](https://github.com/soxoj/maigret), the OSINT tool that checks a username across thousands of sites. Ask your agent to find where a handle is registered, or to analyze a profile URL, and get a saved report back. Maigret runs in Docker, so there is nothing to install besides Docker and Node.
  23. > [!WARNING]
  24. > Use this for legitimate, authorized OSINT research on publicly available information. Follow the law and each site's terms of service, and respect people's privacy. Some sites rate-limit or block automated lookups.
  25. ## Highlights
  26. - **Username search** across hundreds to thousands of sites, filterable by tag (`photo`, `dating`, `us`, ...).
  27. - **URL analysis.** Hand it a profile URL and maigret extracts what it can and looks for linked usernames.
  28. - **Six report formats** (`txt`, `html`, `csv`, `json`, `xmind`, `pdf`), saved to a directory you choose. See [which ones work today](#output-formats).
  29. - **Hardened inputs.** Strict validation and `execFile` with argument arrays. No shell is ever involved. See [Security](#security).
  30. - **Docker-based.** The maigret image is pulled on first use, so every machine runs the same maigret.
  31. ## How it works
  32. ```mermaid
  33. flowchart LR
  34. A["AI agent<br/>(Claude Desktop, Claude Code, any MCP client)"] -->|"MCP over stdio"| S["mcp-maigret"]
  35. S -->|"validate input,<br/>execFile docker run"| D["soxoj/maigret<br/>(Docker)"]
  36. D -->|"checks sites"| W(("Public<br/>websites"))
  37. D -->|"writes report"| R[("MAIGRET_REPORTS_DIR")]
  38. S -->|"report path + scan output"| A
  39. ```
  40. ## Quickstart
  41. **Requirements:** Node.js 18 or newer, plus either [Docker](https://docs.docker.com/get-docker/) installed and running, or maigret installed locally (`pipx install 'maigret[pdf]'`). `MAIGRET_RUNNER` chooses `docker`, `local` or `auto` (default: local if `maigret` is on `PATH`, else Docker); see [Connect a client](docs/clients.md#requirements). Developed and tested on macOS. Linux and Windows (Docker Desktop) should work but are untested.
  42. **1. Pick a reports directory.** The server saves reports here. It is created if missing. The variable is required.
  43. ```sh
  44. export MAIGRET_REPORTS_DIR="$HOME/maigret-reports"
  45. ```
  46. **2. Add the server to your client.**
  47. <details open>
  48. <summary><strong>Claude Code</strong></summary>
  49. ```sh
  50. claude mcp add maigret -e MAIGRET_REPORTS_DIR="$HOME/maigret-reports" -- npx -y mcp-maigret
  51. ```
  52. </details>
  53. <details open>
  54. <summary><strong>Claude Desktop</strong></summary>
  55. Edit the config file (macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`, Windows: `%APPDATA%\Claude\claude_desktop_config.json`), then restart Claude Desktop:
  56. ```json
  57. {
  58. "mcpServers": {
  59. "maigret": {
  60. "command": "npx",
  61. "args": ["-y", "mcp-maigret"],
  62. "env": { "MAIGRET_REPORTS_DIR": "/absolute/path/to/maigret-reports" }
  63. }
  64. }
  65. }
  66. ```
  67. </details>
  68. <details>
  69. <summary><strong>From source</strong></summary>
  70. ```sh
  71. git clone https://github.com/w0h1v/mcp-maigret && cd mcp-maigret
  72. npm install && npm run build
  73. ```
  74. Then point your client at `node /absolute/path/to/mcp-maigret/build/index.js` with the same `MAIGRET_REPORTS_DIR` variable.
  75. </details>
  76. **3. Try it.** Ask your agent: *"Use maigret to check where the username `octocat` is registered, filtered to the `coding` tag."*
  77. The first search pulls the maigret image (about 800 MB), so it takes longer.
  78. ## Tools
  79. ### `search_username`
  80. Search for a username across social networks and sites.
  81. | Parameter | Type | Default | Description |
  82. |---|---|---|---|
  83. | `username` | string, required | | Letters, digits, `_`, `-` and `.` only, up to 100 characters |
  84. | `format` | enum | `txt` | `txt`, `html`, `csv`, `json`, `xmind` or `pdf` (see [formats](#output-formats)) |
  85. | `use_all_sites` | boolean | `false` | Check all sites in maigret's database instead of the top 500 |
  86. | `tags` | string[] | none | Only check sites with these tags. Letters, digits, `_` and `-` only |
  87. ```json
  88. { "username": "octocat", "format": "html", "tags": ["coding"] }
  89. ```
  90. The result contains the path of the saved report and maigret's console output. If the report file was not produced, the result says so instead of reporting success.
  91. ### `parse_url`
  92. Parse a URL to extract information and search for associated usernames.
  93. | Parameter | Type | Default | Description |
  94. |---|---|---|---|
  95. | `url` | string, required | | An `http` or `https` URL without shell metacharacters |
  96. | `format` | enum | `txt` | Same options as above |
  97. ```json
  98. { "url": "https://github.com/octocat" }
  99. ```
  100. Results come back as maigret's scan output text.
  101. ## Output formats
  102. Reports are written to `MAIGRET_REPORTS_DIR`. Maigret picks the file names, and for some formats it adds a suffix. When maigret finds related usernames it can write extra reports next to the main one (for example `report_octocatsup.txt`).
  103. | Format | File written by `search_username` | Status |
  104. |---|---|---|
  105. | `txt` | `report_<username>.txt` | Works. Default. |
  106. | `csv` | `report_<username>.csv` | Works |
  107. | `json` | `report_<username>_simple.json` | Works |
  108. | `html` | `report_<username>_plain.html` | Works |
  109. | `xmind` | `report_<username>.xmind` | Works |
  110. | `pdf` | `report_<username>.pdf` | Works with a local maigret installed with the `pdf` extra, and in this repo's Docker image. **Not available** with the stock `soxoj/maigret` image used by the Docker runner; the tool reports that no file was produced. |
  111. Statuses were checked against maigret 0.6.6 (image `soxoj/maigret:latest`, October 2026). Maigret's command line changes between releases, so this can drift.
  112. ## Security
  113. Usernames, URLs and tags come from an AI agent and are treated as untrusted.
  114. - **Validation.** Usernames allow only `[A-Za-z0-9_.-]` (max 100 characters). Tags allow only `[A-Za-z0-9_-]` (max 50). URLs must parse as `http` or `https` and may not contain shell metacharacters.
  115. - **No shell.** Docker is launched with `execFile` and an argument array, never a concatenated command string.
  116. - **Contained writes.** Reports are written by the container into the single directory you mount. The server does not read or write elsewhere.
  117. What this does not cover: the server runs Docker on your machine on your agent's behalf, and it makes network requests to many third-party sites from your IP address. Run it only for agents and clients you trust.
  118. Found a vulnerability? Report it privately. See [SECURITY.md](SECURITY.md).
  119. ## Troubleshooting
  120. | Message | Fix |
  121. |---|---|
  122. | `Docker is not installed or not running` | Install Docker and start the daemon. Check with `docker --version` and `docker ps`. On Linux, add yourself to the `docker` group: `sudo usermod -aG docker $USER`. |
  123. | `MAIGRET_REPORTS_DIR environment variable must be set` | Add the variable to your client's `env` block, then restart the client. |
  124. | `Error creating reports directory` | Check the path and that your user can write to it. Use an absolute path without a trailing slash. |
  125. | `Invalid username` / `Invalid tag` / `Invalid URL` | Input failed validation. Use only the characters listed under [Tools](#tools). |
  126. | `No report file was produced ...` | The chosen format isn't available in the image (see [formats](#output-formats)). Try `txt`, `json` or `html`. |
  127. | `Error executing maigret` | Read the Docker output included in the message. Often a network problem or a changed maigret option. |
  128. | Searches seem slow | The first run pulls the image. Narrow the search with `tags`, and avoid `use_all_sites` unless you need it. |
  129. More in the [docs](https://w0h1v.github.io/mcp-maigret/troubleshooting/).
  130. ## Contributing
  131. Contributions are welcome. Start with [CONTRIBUTING.md](CONTRIBUTING.md).
  132. - [Changelog](CHANGELOG.md)
  133. - Questions and help: [SUPPORT](.github/SUPPORT.md)
  134. - Security reports: [SECURITY.md](SECURITY.md) (private advisories, never public issues)
  135. <a href="https://glama.ai/mcp/servers/knnpcz651x"><img width="380" height="200" src="https://glama.ai/mcp/servers/knnpcz651x/badge" alt="mcp-maigret MCP server" /></a>
  136. ## License
  137. [MIT](LICENSE). Independent project, not affiliated with the maigret project. Maigret is by [soxoj](https://github.com/soxoj/maigret) and has its own license.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.