LynxPrompt-MCP
A tiny bridge that exposes any LynxPrompt instance as an MCP server, enabling LLMs to browse, search, and manage AI configuration blueprints.
---
## What you get
| Type | What for | MCP URI / Tool id |
|---------------|------------------------------------------------------------|----------------------------------|
| **Resources** | Browse blueprints, hierarchies, and user info read-only | `lynxprompt://blueprints`
`lynxprompt://blueprint/{id}`
`lynxprompt://hierarchies`
`lynxprompt://hierarchy/{id}`
`lynxprompt://user` |
| **Tools** | Create, update, delete blueprints and manage hierarchies | `search_blueprints`
`create_blueprint`
`update_blueprint`
`delete_blueprint`
`create_hierarchy`
`delete_hierarchy` |
Everything is exposed over a single JSON-RPC endpoint (`/mcp`).
LLMs / Agents can: `initialize` -> `readResource` -> `listTools` -> `callTool` ... and so on.
---
## Quick-start (Docker Compose)
```yaml
services:
lynxprompt-mcp:
image: drumsergio/lynxprompt-mcp:latest
ports:
- "127.0.0.1:8080:8080"
environment:
- LYNXPROMPT_URL=https://lynxprompt.com
- LYNXPROMPT_TOKEN=lp_xxx
```
> **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.
## Install via npm (stdio transport)
```sh
npx lynxprompt-mcp
```
Or install globally:
```sh
npm install -g lynxprompt-mcp
lynxprompt-mcp
```
This 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).
## Local build
```sh
git clone https://github.com/GeiserX/lynxprompt-mcp
cd lynxprompt-mcp
# (optional) create .env from the sample
cp .env.example .env && $EDITOR .env
go run ./cmd/server
```
## Configuration
| Variable | Default | Description |
|-------------------|--------------------------|--------------------------------------------------|
| `LYNXPROMPT_URL` | `https://lynxprompt.com` | LynxPrompt instance URL (without trailing /) |
| `LYNXPROMPT_TOKEN`| _(required)_ | API token in `lp_xxx` format |
| `LISTEN_ADDR` | `127.0.0.1:8080` | HTTP listen address (Docker sets `127.0.0.1:8080`) |
| `MCP_AUTH_TOKEN` | _(empty)_ | Bearer token for HTTP auth (required if LISTEN_ADDR is not loopback) |
| `TRANSPORT` | _(empty = HTTP)_ | Set to `stdio` for stdio transport |
Put them in a `.env` file (from `.env.example`) or set them in the environment.
## Testing
Tested 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.
## Example configuration for client LLMs
```json
{
"schema_version": "v1",
"name_for_human": "LynxPrompt-MCP",
"name_for_model": "lynxprompt_mcp",
"description_for_human": "Browse, search, and manage AI configuration blueprints from LynxPrompt.",
"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.",
"auth": { "type": "bearer", "token": "your-secret-token" },
"api": {
"type": "jsonrpc-mcp",
"url": "http://localhost:8080/mcp",
"init_method": "initialize",
"session_header": "Mcp-Session-Id"
},
"logo_url": "https://lynxprompt.com/logo.png",
"contact_email": "acsdesk@protonmail.com",
"legal_info_url": "https://github.com/GeiserX/lynxprompt-mcp/blob/main/LICENSE"
}
```
## Credits
[LynxPrompt](https://lynxprompt.com) -- AI configuration blueprint management
[MCP-GO](https://github.com/mark3labs/mcp-go) -- modern MCP implementation
[GoReleaser](https://goreleaser.com/) -- painless multi-arch releases
## Maintainers
[@GeiserX](https://github.com/GeiserX).
## Contributing
Feel free to dive in! [Open an issue](https://github.com/GeiserX/lynxprompt-mcp/issues/new) or submit PRs.
LynxPrompt-MCP follows the [Contributor Covenant](http://contributor-covenant.org/version/2/1/) Code of Conduct.
## Other MCP Servers by GeiserX
- [cashpilot-mcp](https://github.com/GeiserX/cashpilot-mcp) — Passive income monitoring
- [duplicacy-mcp](https://github.com/GeiserX/duplicacy-mcp) — Backup health monitoring
- [genieacs-mcp](https://github.com/GeiserX/genieacs-mcp) — TR-069 device management
- [pumperly-mcp](https://github.com/GeiserX/pumperly-mcp) — Fuel and EV charging prices
- [telegram-archive-mcp](https://github.com/GeiserX/telegram-archive-mcp) — Telegram message archive
## Related Projects
| Project | Description |
|---------|-------------|
| [LynxPrompt](https://github.com/GeiserX/LynxPrompt) | Self-hosted platform for AI IDE/Tools Rules and Commands via WebUI and CLI |
| [lynxprompt-vscode](https://github.com/GeiserX/lynxprompt-vscode) | VS Code extension for LynxPrompt AI configuration file management |
| [lynxprompt-action](https://github.com/GeiserX/lynxprompt-action) | GitHub Action to sync and validate AI IDE configuration files with LynxPrompt |
| [n8n-nodes-lynxprompt](https://github.com/GeiserX/n8n-nodes-lynxprompt) | n8n community node for LynxPrompt AI configuration blueprints |
| [homebrew-lynxprompt](https://github.com/GeiserX/homebrew-lynxprompt) | Homebrew tap for LynxPrompt CLI |