{ "markdown": "

\n \"LynxPrompt\n

\n\n

LynxPrompt-MCP

\n\n

\n \"codecov\"/\n \"npm\"/\n \"Go\"/\n \"Docker\n \"GitHub\n \"License\"/\n

\n

\n \"Official\n \"Glama\n \"MCPServers.org\"/\n \"mcp.so\"/\n \"ToolSDK\n \"listed\n

\n\n

A tiny bridge that exposes any LynxPrompt instance as an MCP server, enabling LLMs to browse, search, and manage AI configuration blueprints.

\n\n---\n\n## What you get\n\n| Type | What for | MCP URI / Tool id |\n|---------------|------------------------------------------------------------|----------------------------------|\n| **Resources** | Browse blueprints, hierarchies, and user info read-only | `lynxprompt://blueprints`
`lynxprompt://blueprint/{id}`
`lynxprompt://hierarchies`
`lynxprompt://hierarchy/{id}`
`lynxprompt://user` |\n| **Tools** | Create, update, delete blueprints and manage hierarchies | `search_blueprints`
`create_blueprint`
`update_blueprint`
`delete_blueprint`
`create_hierarchy`
`delete_hierarchy` |\n\nEverything is exposed over a single JSON-RPC endpoint (`/mcp`).\nLLMs / Agents can: `initialize` -> `readResource` -> `listTools` -> `callTool` ... and so on.\n\n---\n\n## Quick-start (Docker Compose)\n\n```yaml\nservices:\n lynxprompt-mcp:\n image: drumsergio/lynxprompt-mcp:latest\n ports:\n - \"127.0.0.1:8080:8080\"\n environment:\n - LYNXPROMPT_URL=https://lynxprompt.com\n - LYNXPROMPT_TOKEN=lp_xxx\n```\n\n> **Security note:** The HTTP transport listens on `127.0.0.1:8080` by default. If you need to expose it on a network, place it behind a reverse proxy with authentication.\n\n## Install via npm (stdio transport)\n\n```sh\nnpx lynxprompt-mcp\n```\n\nOr install globally:\n\n```sh\nnpm install -g lynxprompt-mcp\nlynxprompt-mcp\n```\n\nThis downloads the pre-built Go binary from GitHub Releases for your platform and runs it with stdio transport. Requires at least one [published release](https://github.com/GeiserX/lynxprompt-mcp/releases).\n\n## Local build\n\n```sh\ngit clone https://github.com/GeiserX/lynxprompt-mcp\ncd lynxprompt-mcp\n\n# (optional) create .env from the sample\ncp .env.example .env && $EDITOR .env\n\ngo run ./cmd/server\n```\n\n## Configuration\n\n| Variable | Default | Description |\n|-------------------|--------------------------|--------------------------------------------------|\n| `LYNXPROMPT_URL` | `https://lynxprompt.com` | LynxPrompt instance URL (without trailing /) |\n| `LYNXPROMPT_TOKEN`| _(required)_ | API token in `lp_xxx` format |\n| `LISTEN_ADDR` | `127.0.0.1:8080` | HTTP listen address (Docker sets `127.0.0.1:8080`) |\n| `MCP_AUTH_TOKEN` | _(empty)_ | Bearer token for HTTP auth (required if LISTEN_ADDR is not loopback) |\n| `TRANSPORT` | _(empty = HTTP)_ | Set to `stdio` for stdio transport |\n\nPut them in a `.env` file (from `.env.example`) or set them in the environment.\n\n## Testing\n\nTested with [Inspector](https://modelcontextprotocol.io/docs/tools/inspector) and it is currently fully working. Before making a PR, make sure this MCP server behaves well via this medium.\n\n## Example configuration for client LLMs\n\n```json\n{\n \"schema_version\": \"v1\",\n \"name_for_human\": \"LynxPrompt-MCP\",\n \"name_for_model\": \"lynxprompt_mcp\",\n \"description_for_human\": \"Browse, search, and manage AI configuration blueprints from LynxPrompt.\",\n \"description_for_model\": \"Interact with a LynxPrompt instance that stores AI configuration blueprints. First call initialize, then reuse the returned session id in header \\\"Mcp-Session-Id\\\" for every other call. Use readResource to fetch URIs that begin with lynxprompt://. Use listTools to discover available actions and callTool to execute them.\",\n \"auth\": { \"type\": \"bearer\", \"token\": \"your-secret-token\" },\n \"api\": {\n \"type\": \"jsonrpc-mcp\",\n \"url\": \"http://localhost:8080/mcp\",\n \"init_method\": \"initialize\",\n \"session_header\": \"Mcp-Session-Id\"\n },\n \"logo_url\": \"https://lynxprompt.com/logo.png\",\n \"contact_email\": \"acsdesk@protonmail.com\",\n \"legal_info_url\": \"https://github.com/GeiserX/lynxprompt-mcp/blob/main/LICENSE\"\n}\n```\n\n## Credits\n\n[LynxPrompt](https://lynxprompt.com) -- AI configuration blueprint management\n\n[MCP-GO](https://github.com/mark3labs/mcp-go) -- modern MCP implementation\n\n[GoReleaser](https://goreleaser.com/) -- painless multi-arch releases\n\n## Maintainers\n\n[@GeiserX](https://github.com/GeiserX).\n\n## Contributing\n\nFeel free to dive in! [Open an issue](https://github.com/GeiserX/lynxprompt-mcp/issues/new) or submit PRs.\n\nLynxPrompt-MCP follows the [Contributor Covenant](http://contributor-covenant.org/version/2/1/) Code of Conduct.\n\n## Other MCP Servers by GeiserX\n\n- [cashpilot-mcp](https://github.com/GeiserX/cashpilot-mcp) — Passive income monitoring\n- [duplicacy-mcp](https://github.com/GeiserX/duplicacy-mcp) — Backup health monitoring\n- [genieacs-mcp](https://github.com/GeiserX/genieacs-mcp) — TR-069 device management\n- [pumperly-mcp](https://github.com/GeiserX/pumperly-mcp) — Fuel and EV charging prices\n- [telegram-archive-mcp](https://github.com/GeiserX/telegram-archive-mcp) — Telegram message archive\n\n## Related Projects\n\n| Project | Description |\n|---------|-------------|\n| [LynxPrompt](https://github.com/GeiserX/LynxPrompt) | Self-hosted platform for AI IDE/Tools Rules and Commands via WebUI and CLI |\n| [lynxprompt-vscode](https://github.com/GeiserX/lynxprompt-vscode) | VS Code extension for LynxPrompt AI configuration file management |\n| [lynxprompt-action](https://github.com/GeiserX/lynxprompt-action) | GitHub Action to sync and validate AI IDE configuration files with LynxPrompt |\n| [n8n-nodes-lynxprompt](https://github.com/GeiserX/n8n-nodes-lynxprompt) | n8n community node for LynxPrompt AI configuration blueprints |\n| [homebrew-lynxprompt](https://github.com/GeiserX/homebrew-lynxprompt) | Homebrew tap for LynxPrompt CLI |\n", "bytes": 8027, "sha": "2a09e40fe4ddf69f262bc6de33076d5316890f9cd833169225ea477631428314", "repo_slug": "geiserx/lynxprompt-mcp", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_geiserx_lynxprompt_mcp_625e37de/readme" }