DefiLlama MCP Server
This package provides a Model Context Protocol (MCP) server that acts as a proxy to the public DefiLlama API. It allows AI assistants (like Cursor) to interact with the DefiLlama API through the defined OpenAPI specification.
Features
- Dynamically generates MCP tools from the DefiLlama OpenAPI specification.
- Uses the official DefiLlama API.
- Translates MCP
callToolrequests into HTTP requests to the DefiLlama API. - Handles responses and errors from the API.
Installation & Usage
Using npx (Recommended for Clients like Cursor)
Once published to npm, you can configure clients like Cursor to automatically download and run the server using npx. Add an entry to your client’s MCP configuration (e.g., mcp.json):
{
"mcpServers": {
"defillama": {
"command": "npx",
"args": [
"-y", // Ensures the latest version is used without prompting
"@nic0xflamel/defillama-mcp-server"
// Add any server-specific arguments here if needed in the future
]
}
// ... other servers
}
}
Replace "defillama" with your desired server name key.
Using Smithery (for Claude Desktop)
To install automatically via Smithery:
npx -y @smithery/cli install @nic0xflamel/defillama-mcp-server --client claude
Manual / Development
- Clone the repository.
- Run
npm install. - Run
npm run build. - Start the server:
npm startor use the linked commanddefillama-mcp-server(after runningnpm link). - Configure your MCP client to connect via
stdiousing the appropriate command (seenpxexample above, adapting for local paths or linked command if not usingnpx).
License
MIT (A LICENSE file exists in the project root)
DefiLlama API Server
Project Details
- nic0xflamel/defillama-mcp
- MIT License
- Last Updated: 5/8/2025
Recomended MCP Servers
Connect APIs, remarkably fast. Free for developers.
A Model Context Protocol (MCP) server implementation providing persistent note management created with Python SDK.
Execute SQL queries and manage databases seamlessly with Timeplus. Leverage powerful tools to interact with your data, Kafka...
MCP - Bridge all your webhook endpoints into 1 unified config
makes the jewish library accessible to LLMs through the MCP protocol
MCP server to connect AI agents to any github corpa
Model Context Protocol server to run commands
MCP server for Buienradar's precipitation endpoint
mcp-tutorial
MCP server to provide Figma layout information to AI coding agents like Cursor





