How is risk scored?
Philidor uses the Vector Risk Framework: 40% asset quality, 40% platform code maturity, and 20% governance controls. Final scores range 0–10, categorized as Prime (8.0–10.0), Core (5.0–7.9), or Edge (0–4.9).

@Philidor-Labs
Basic information
DeFi vault risk analytics for AI agents
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"philidor-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/philidor-labs/philidor-mcp"
]
}
}
}Search and filter DeFi vaults by chain, protocol, asset, risk tier, TVL, and more. Returns a paginated list with risk scores and APR.
Get detailed information about a specific DeFi vault including risk breakdown, recent events, and historical snapshots. Lookup by ID or by network + address.
Get a detailed breakdown of a vault's risk vectors: Asset Composition, Platform Code, and Governance scores with sub-metrics.
Compare 2-3 DeFi vaults side-by-side on TVL, APR, risk score, risk tier, audited status, and more.
Find the safest (highest risk-scored) DeFi vaults, optionally filtered by asset, chain, or minimum TVL. Returns top 10 audited, high-confidence vaults sorted by risk score.
Get detailed information about a DeFi protocol including TVL, vault count, versions, auditors, and security incidents.
Get detailed information about a vault curator including their managed vaults, TVL, chain distribution, and performance.
Get a high-level overview of the DeFi vault market: total TVL, vault count, risk distribution, and TVL by protocol.
Explain what a Philidor risk score means, including the tier (Prime/Core/Edge), how it is calculated, and what the thresholds are.
Philidor MCP is a Model Context Protocol server that provides DeFi vault risk analytics for AI agents. It lets you search 700+ vaults across protocols like Morpho, Aave, Yearn, and Beefy, compare risk scores, analyze protocols, and run due diligence through natural language—with no API key required.
Connect AI assistants like Claude or Cursor to the hosted server at https://mcp.philidor.io/api/mcp. Alternatively, run the server locally via Docker (docker run -i --rm ghcr.io/philidor-labs/philidor-mcp) or from source (npm install && npm start). Add the server URL to your MCP client configuration (e.g., Claude Desktop, Claude Code, Cursor, or Windsurf).
Philidor uses the Vector Risk Framework: 40% asset quality, 40% platform code maturity, and 20% governance controls. Final scores range 0–10, categorized as Prime (8.0–10.0), Core (5.0–7.9), or Edge (0–4.9).
No. The hosted server and the Philidor Public API require no API key. You can connect immediately using the provided URL.
Supported protocols include Morpho, Aave v3, Yearn v3, Beefy, Spark, Fluid, and Euler. Supported chains include Ethereum, Base, Polygon, Gnosis, Arbitrum, and more.
Data is fetched from the Philidor Public API, which aggregates on-chain data. The server is stateless—each request pulls fresh data with no session state.
Yes. Use Docker (`docker run -i --rm ghcr.io/philidor-labs/philidor-mcp`) or clone the repo, run `npm install && npm start`. You can point to a custom API endpoint via the `PHILIDOR_API_URL` environment variable.
Open-source MCP to use Blender with any LLM
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
MCP Toolbox for Databases is an open source MCP server for databases.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Hindsight: Agent Memory That Learns
Comments