chainlist-mcp

Chainlist MCP Server

An MCP server that gives AI agents fast access to verified EVM chain information, including RPC URLs, chain IDs, explorers, and native tokens — sourced from Chainlist.org.

Features

• Efficient Data Fetching: Caches Chainlist API data to minimize requests.
• Flexible Search: Case-insensitive keyword matching using regex for getChainsByKeyword.
• Structured Output: Markdown responses with tabulated rpc and explorers for readability.

Installation

Prerequisites

• Python: Version 3.10 or higher.
• uv: Recommended for managing Python projects and dependencies (install via pip install uv or follow uv documentation).

Steps

1. Clone the Repository:
   git clone https://github.com/kukapay/chainlist-mcp.git cd chainlist-mcp
2. Install Dependencies:
   uv sync
3. Installing to Claude Desktop: Install the server as a Claude Desktop application:
   uv run mcp install cli.py --name "Chainlist MCP"
   Configuration file as a reference:
   { "mcpServers": { "Chainlist MCP": { "command": "uv", "args": [ "--directory", "/path/to/chainlist-mcp", "run", "main.py" ] } } }
   Replace /path/to/chainlist-mcp with your actual installation path.

Usage

The server exposes two tools via the MCP protocol, accessible through MCP-compatible clients or the MCP Inspector.

Tools

getChainById

• Description: Retrieves details of a blockchain by its chain ID.
• Parameters:
  • chain_id (integer): The unique identifier of the blockchain (e.g., 1 for Ethereum Mainnet).
• Returns: A Markdown string with chain details or an error message.

Example Prompt (in an MCP client):

Example Response:

getChainsByKeyword

• Description: Searches for blockchains by keyword (case-insensitive partial match).
• Parameters:
  • keyword (string): The keyword or partial name to search (e.g., 'eth').
  • limit (integer, optional): Maximum number of results (default: 5).
• Returns: A Markdown string listing up to limit matching chains or an error message.

Example Prompt (in an MCP client):

Example Response:

License

This project is licensed under the MIT License. See the LICENSE file for details.