Core Lightning MCP Server
A Rust-based gRPC server that provides a standardized MCP interface for Core Lightning nodes.
Core Lightning MCP Server
A Rust-based gRPC server that provides a standardized interface to Core Lightning nodes. This server implements the MCP (Model Context Protocol) specification to enable control of the Core Lightning node using LLM.

Installation
Option 1: From Release (Recommended)
- Download the appropriate binary for your platform from the latest release
- Extract the archive:
# For Linux/macOS tar -xzf cln-mcp-<platform>.tar.gz # For Windows # Use your preferred zip extractor - Make the binary executable (Linux/macOS only):
chmod +x cln-mcp
Option 2: From Source
Prerequisites
- Rust 1.80 or higher
- Protocol Buffers Compiler (protoc)
- Core Lightning (with gRPC enabled)
- MCP clients (Claude, Goose, etc.)
Protocol Buffers Compiler (protoc)
Ubuntu/Debian:
sudo apt-get update
sudo apt-get install -y protobuf-compiler
macOS:
brew install protobuf
Windows:
choco install protoc
Verify installation:
protoc --version # Should show version 3.0.0 or higher
- Clone the repository:
git clone https://github.com/adi2011/cln-mcp.git
cd cln-mcp
- Build the project:
cargo build --release
Configuration
The server can be configured using command-line arguments:
cln-mcp [OPTIONS]
Options:
--certs-dir <path> Path to certificates directory
--node-address <url> Node address (default: https://localhost:9736)
--help Shows help message
TLS Certificate Setup
Add the --grpc-port(default: 9736) option while running CLN, and it'll automatically generate the appropriate mTLS certificates.
Copy the following PEM files from the Lightning directory to a separate directory:
ca.pem: CA certificateclient.pem: Client certificateclient-key.pem: Client private key
Claude Setup
- Install Claude
- Go to settings -> Developer
- Edit Config
{
"mcpServers" : {
"cln-mcp" : {
"command": "Path/to/cln-mcp" (ex: "/Users/MyPC/cln-mcp/target/release/cln-mcp" or the executable unzipped from the release),
"args": [
"--certs-dir",
"Path/to/certificates" (ex: "/Users/MyPC/cln-mcp/certs")
]
}
}
}
- Restart Claude
Future Goals
[ ] Enable it to derive parameters for the RPC calls
[ ] Choose the most appropriate and useful RPCs for maximum utility
[ ] Extend support for LND
[ ] Host multiple servers to make it more efficient
This is a work in progress. We welcome code reviews, pull requests, and issues based on your usage.
Máy chủ liên quan
Alpha Vantage MCP Server
nhà tài trợAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
browser-devtools-mcp
A Playwright-based MCP server that exposes a live browser as a traceable, inspectable, debuggable and controllable execution environment for AI agents.
Sistema de Predicción Energética con IA
An AI-powered system for analyzing and predicting domestic energy consumption. It offers precise forecasts, historical pattern analysis, and personalized optimization recommendations through a conversational interface.
MCPR
Expose R functions through the Model Context Protocol (MCP) for seamless integration with AI assistants.
TokenTool MCP
Deploy and manage compliant tokens from Claude, Cursor, or any AI agent — by typing a sentence.
MCP Java Dev Tools
Bridges agentic coding tools and live Java runtime behavior through a lightweight sidecar agent.
ASKME-CLI
A command-line interface to prompt users for their next plan or confirmation.
Skills-ContextManager
Don’t pollute your AI agent’s context with 1,000 skills. Use Skills-ContextManager, a self-hosted web UI for managing AI skills and workflows by providing skills to an AI agent via MCP only when needed. Simply add skills to your library and enable or disable them with a toggle. Choose whether a skill is always loaded into context or dynamically activated when the AI agent determines it’s needed.
MCP Inspector
A developer tool for testing and debugging MCP servers with a web UI and proxy.
Cygnus MCP Server
An MCP server demonstrating Cygnus tools for reading text files and invoking local APIs.
Model Context Protocol servers
A collection of reference MCP server implementations in TypeScript and Python, demonstrating MCP features and SDKs.