English Français العربية

LynxPrompt

Official registry Search and web

Search, read and manage AI agent instruction blueprints (AGENTS.md, CLAUDE.md) on LynxPrompt

Source code Website Documentation

What can you do with LynxPrompt?

  • Read-only resources for blueprints, hierarchies and the current user (lynxprompt://blueprints, lynxprompt://hierarchies, lynxprompt://user).
  • Tools to search, create, update and delete blueprints, and to create and delete hierarchies.
  • One JSON-RPC endpoint (/mcp) over HTTP, or stdio with TRANSPORT=stdio.
  • Listens on loopback by default; MCP_AUTH_TOKEN adds bearer auth when you expose it.
  • Ships as a Docker image, an npm package (npx lynxprompt-mcp) and multi-arch Go binaries.

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package lynxprompt-mcp
Claude Code 
claude mcp add lynxprompt -e 'LYNXPROMPT_TOKEN=<your lynxprompt_token>' -e 'LYNXPROMPT_URL=https://lynxprompt.com' -e 'LYNXPROMPT_READ_ONLY=false' -- npx -y lynxprompt-mcp@0.2.0
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "lynxprompt": {
            "command": "npx",
            "args": [
                "-y",
                "lynxprompt-mcp@0.2.0"
            ],
            "env": {
                "LYNXPROMPT_TOKEN": "<your lynxprompt_token>",
                "LYNXPROMPT_URL": "https://lynxprompt.com",
                "LYNXPROMPT_READ_ONLY": "false"
            }
        }
    }
}

Environment variables

  • LYNXPROMPT_TOKEN required secret LynxPrompt API token (lp_...), created under Settings > API tokens. Needed for everything except search_blueprints.
  • LYNXPROMPT_URL LynxPrompt instance URL; https:// unless the host is loopback.
  • LYNXPROMPT_READ_ONLY Set to true to register only the read tools (no create, update or delete).
OCI package drumsergio/lynxprompt-mcp:v0.2.0
Claude Code 
claude mcp add lynxprompt -e 'LYNXPROMPT_TOKEN=<your lynxprompt_token>' -e 'LYNXPROMPT_URL=https://lynxprompt.com' -e 'LYNXPROMPT_READ_ONLY=false' -- docker run -i --rm drumsergio/lynxprompt-mcp:v0.2.0
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "lynxprompt": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "drumsergio/lynxprompt-mcp:v0.2.0"
            ],
            "env": {
                "LYNXPROMPT_TOKEN": "<your lynxprompt_token>",
                "LYNXPROMPT_URL": "https://lynxprompt.com",
                "LYNXPROMPT_READ_ONLY": "false"
            }
        }
    }
}

Environment variables

  • LYNXPROMPT_TOKEN required secret LynxPrompt API token (lp_...), created under Settings > API tokens. Needed for everything except search_blueprints.
  • LYNXPROMPT_URL LynxPrompt instance URL; https:// unless the host is loopback.
  • LYNXPROMPT_READ_ONLY Set to true to register only the read tools (no create, update or delete).

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. lynxprompt-mcp
  2. Features
  3. Quick start
  4. Documentation
  5. Related projects
  6. License

lynxprompt-mcp

An MCP server for any LynxPrompt instance. LLMs use it to browse, search and manage AI configuration blueprints.

It works with lynxprompt.com or your own self-hosted LynxPrompt, over HTTP or stdio.

Features

  • Read-only resources for blueprints, hierarchies and the current user (lynxprompt://blueprints, lynxprompt://hierarchies, lynxprompt://user).
  • Tools to search, create, update and delete blueprints, and to create and delete hierarchies.
  • One JSON-RPC endpoint (/mcp) over HTTP, or stdio with TRANSPORT=stdio.
  • Listens on loopback by default; MCP_AUTH_TOKEN adds bearer auth when you expose it.
  • Ships as a Docker image, an npm package (npx lynxprompt-mcp) and multi-arch Go binaries.

Quick start

Register the npm package in your MCP client (Claude Desktop, Claude Code, Cursor); npx runs it over stdio:

{
  "mcpServers": {
    "lynxprompt": {
      "command": "npx",
      "args": ["-y", "lynxprompt-mcp"],
      "env": { "LYNXPROMPT_TOKEN": "lp_..." }
    }
  }
}

For a self-hosted instance add LYNXPROMPT_URL to env. Docker Compose, the HTTP server and local builds are in Getting started.

Documentation

LynxPrompt, the self-hosted platform this server talks to.

License

GPL-3.0-or-later

Frequently asked questions

What is LynxPrompt?

Search, read and manage AI agent instruction blueprints (AGENTS.md, CLAUDE.md) on LynxPrompt

How do I install LynxPrompt?

It runs on your machine. In Claude Code: claude mcp add lynxprompt -e 'LYNXPROMPT_TOKEN=<your lynxprompt_token>' -e 'LYNXPROMPT_URL=https://lynxprompt.com' -e 'LYNXPROMPT_READ_ONLY=false' -- npx -y lynxprompt-mcp@0.2.0. For other clients, paste the JSON configuration from this page into their MCP settings.

Does LynxPrompt need an API key?

Yes. It expects LYNXPROMPT_TOKEN, which you set in its configuration.

Is LynxPrompt open source?

Yes. Its code is on GitHub under the GPL-3.0 license.

Who maintains LynxPrompt?

It is published by GeiserX. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.