DeFi Yields MCP
About
An MCP server for AI agents to explore DeFi yield opportunities, powered by DefiLlama.
Details
- License
- MIT
Explore
- Data Fetching Tool: The get_yield_pools tool retrieves DeFi yield pool data from the DefiLlama, allowing filtering by chain (e.g., Ethereum, Solana) or project (e.g., Lido, Aave).
- Analysis Prompt: The analyze_yields prompt generates tailored instructions for AI agents to analyze yield pool data, focusing on key metrics like APY, 30-day mean APY, and predictions.
- Packaged for Ease: Run the server directly with uvx defi-yields-mcp.
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
DeFi Yields MCPCommand (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
To use the server with Claude Desktop, you can either install it automatically or manually configure the Claude Desktop configuration file.
Install the server for Claude Desktop:
uvx mcp install -m defi_yields_mcp --name "DeFi Yields Server"
Locate the configuration file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the server configuration:
{
"mcpServers": {
"defi-yields-mcp": {
"command": "uvx",
"args": [ "defi-yields-mcp" ]
}
}
}
Restart Claude Desktop.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"defi yields mcp": {
"defi-yields-mcp": {
"command": "uvx",
"args": [
"mcp",
"install",
"-m",
"defi_yields_mcp",
"--name",
"DeFi Yields Server"
]
}
}
}
}McpServers
{
"defi-yields-mcp": {
"command": "uvx",
"args": [
"mcp",
"install",
"-m",
"defi_yields_mcp",
"--name",
"DeFi Yields Server"
]
}
}An MCP server for AI agents to explore DeFi yield opportunities, powered by DefiLlama.
Features
- Data Fetching Tool: The get_yield_pools tool retrieves DeFi yield pool data from the DefiLlama, allowing filtering by chain (e.g., Ethereum, Solana) or project (e.g., Lido, Aave).
- Analysis Prompt: The analyze_yields prompt generates tailored instructions for AI agents to analyze yield pool data, focusing on key metrics like APY, 30-day mean APY, and predictions.
- Packaged for Ease: Run the server directly with uvx defi-yields-mcp.
Installation
To use the server with Claude Desktop, you can either install it automatically or manually configure the Claude Desktop configuration file.
Option 1: Automatic Installation
Install the server for Claude Desktop:uvx mcp install -m defi_yields_mcp --name "DeFi Yields Server"
Option 2: Manual Configuration
Locate the configuration file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the server configuration:
{
"mcpServers": {
"defi-yields-mcp": {
"command": "uvx",
"args": [ "defi-yields-mcp" ]
}
}
}
Restart Claude Desktop.
Examples
You can use commands like:
- "Fetch yield pools for the Lido project."
- "Analyze yield pools on Ethereum."
- "What are the 30-day mean APYs for Solana pools?"
The get_yield_pools tool fetches and filters the data, while the analyze_yields prompt guides the LLM to provide a detailed analysis.
Example Output
Running the get_yield_pools tool with a filter for Ethereum:
[
{
"chain": "Ethereum",
"pool": "STETH",
"project": "lido",
"tvlUsd": 14804019222,
"apy": 2.722,
"apyMean30d": 3.00669,
"predictions": {
"predictedClass": "Stable/Up",
"predictedProbability": 75,
"binnedConfidence": 3
}
},
...
]
License
This project is licensed under the MIT License. See the LICENSE file for details.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
