kukapay/defi-yields-mcp
by Various
An MCP server for AI agents to explore DeFi yield opportunities, powered by DefiLlama.
MCP
kukapay/defi-yields-mcp
Added 1 June 2026
Overview
An MCP server that lets AI agents query DeFi yield opportunities using data from DefiLlama. It exposes yield rates and protocol comparisons through the Model Context Protocol standard. Built in Python, it is open source and designed for integration into agent workflows.
Best for
Best for
Developers building AI agents that need real-time DeFi yield data via a standardized protocol
Use cases
- Fetch current yield rates for a specific DeFi protocol
- Compare yields across multiple protocols in a single query
- Integrate yield data into an AI agent's decision loop
How to use
Install
uvx mcp install -m defi_yields_mcp --name "DeFi Yields Server" Tools exposed
get_yield_poolsanalyze_yields
Tested with
Claude Desktop
Example client config
{\n "mcpServers": {\n "defi-yields-mcp": {\n "command": "uvx",\n "args": [ "defi-yields-mcp" ]\n }\n }\n} Notes
An MCP server that lets AI agents query DeFi yield opportunities using data from DefiLlama. It exposes yield rates and protocol comparisons through the Model Context Protocol standard. Built in Python, it is open source and designed for integration into agent workflows.
14 stars on GitHub. Last updated 2025-04-19. Licensed MIT.
Use cases
- Fetch current yield rates for a specific DeFi protocol
- Compare yields across multiple protocols in a single query
- Integrate yield data into an AI agent’s decision loop
Pros
- Leverages DefiLlama’s comprehensive yield data without building a custom scraper
- Follows the MCP standard, making it compatible with many AI agent frameworks
- Open source and lightweight Python implementation
Cons
- Low GitHub stars (14) indicate limited community adoption and testing
- Depends on DefiLlama’s API availability and rate limits
- Documentation and usage examples may be sparse
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Leverages DefiLlama's comprehensive yield data without building a custom scraper
- Follows the MCP standard, making it compatible with many AI agent frameworks
- Open source and lightweight Python implementation
Cons
- Low GitHub stars (14) indicate limited community adoption and testing
- Depends on DefiLlama's API availability and rate limits
- Documentation and usage examples may be sparse
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Claude Computer Use
Anthropic
Claude takes the mouse and keyboard. A vision-based agent that controls a real desktop, not just a browser.
Cline
Cline
Open-source autonomous coding agent that lives inside VS Code. BYO model key, watch it work.
Claude Code
Anthropic
Anthropic's terminal-native coding agent. Reads your repo, edits files, runs tests, ships PRs.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.