MCP Server for DefiLlama
Description
# MCP Server for DefiLlama This repository contains a Model Context Protocol (MCP) server that provides Claude with access to DeFi data via the DefiLlama API. The server enables Claude to perform operations like retrieving protocol TVL data, chain TVL data, token prices, and…
About
# MCP Server for DefiLlama This repository contains a Model Context Protocol (MCP) server that provides Claude with access to DeFi data via the DefiLlama API. The server enables Claude to perform operations like retrieving protocol TVL data, chain TVL data, token prices, and stablecoin information. ## Overview The MCP…
Details
- Author
- dcSpark
- GitHub stars
- 9
- Downloads
- 219
- Categories
- Other
Jump to
- List all protocols tracked by DefiLlama
- Get TVL data for a specific protocol
- Get TVL data for a specific chain
- Fetch current token prices
- Retrieve historical token prices
- List and query stablecoin data
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP Server for DefiLlamaCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Run the server via npx (npx @mcp-dockmaster/mcp-server-defillama) or by cloning the repo, installing dependencies, and building. To use it with Claude Desktop, add a JSON entry under Settings > Developer Settings > MCP Servers using the npx command or a local path to the built index.js.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp server for defillama": {
"mcp-server-defillama": {
"command": "npx",
"args": [
"@mcp-dockmaster/mcp-server-defillama"
]
}
}
}
}
McpServers
{
"mcp-server-defillama": {
"command": "npx",
"args": [
"@mcp-dockmaster/mcp-server-defillama"
]
}
}
MCP Server for DefiLlama
This repository contains a Model Context Protocol (MCP) server that provides Claude with access to DeFi data via the DefiLlama API. The server enables Claude to perform operations like retrieving protocol TVL data, chain TVL data, token prices, and stablecoin information.
Overview
The MCP server exposes the following tools to Claude:
Protocol Data
- defillama_get_protocols: List all protocols tracked by DefiLlama
- defillama_get_protocol_tvl: Get TVL data for a specific protocol
Chain Data
- defillama_get_chain_tvl: Get TVL data for a specific chain
Token Data
- defillama_get_token_prices: Get current prices of tokens
- defillama_get_historical_prices: Get historical prices of tokens
Stablecoin Data
- defillama_get_stablecoins: List all stablecoins tracked by DefiLlama
- defillama_get_stablecoin_data: Get data for a specific stablecoin
Prerequisites
- Node.js (v16 or higher)
Running the server
Option 1: Using npx (Recommended)
``npx @mcp-dockmaster/mcp-server-defillamaYou can run the MCP server directly without installation using npx:
This will download and execute the server directly from npm.
Option 2: Manual Installation
Clone this repository:
git clone https://github.com/mcp-dockmaster/mcp-server-defillama.gitInstall dependencies:
npm installBuild the project:
npm run build
Claude Usage
To configure Claude Desktop to use this MCP server:
Open Claude Desktop, and navigate to Settings>Developer Settings>MCP Servers. There you'll encounter the button to open the configuration JSON file.
Add the MCP server configuration:
json
{
"mcpServers": {
"mcp-server-defillama": {
"command": "npx",
"args": [
"@mcp-dockmaster/mcp-server-defillama"
]
}
}
}
Alternatively, if you installed the package locally:
json
{
"mcpServers": {
"mcp-server-defillama": {
"command": "node",
"args": [
"/path/to/your/mcp-server-defillama/build/index.js"
]
}
}
}
``Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



