{
  "markdown": "<div align=\"center\">\n\n# Philidor MCP Server\n\n### DeFi vault risk analytics for AI agents\n\n[![MIT License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n[![MCP](https://img.shields.io/badge/MCP-Compatible-8A2BE2)](https://modelcontextprotocol.io)\n[![TypeScript](https://img.shields.io/badge/TypeScript-5.0-blue.svg)](https://www.typescriptlang.org)\n[![Hosted](https://img.shields.io/badge/Hosted-mcp.philidor.io-green.svg)](https://mcp.philidor.io)\n[![smithery badge](https://smithery.ai/badge/philidor/defi)](https://smithery.ai/servers/philidor/defi)\n[![LobeHub](https://lobehub.com/badge/mcp/philidor-labs-philidor-mcp)](https://lobehub.com/mcp/philidor-labs-philidor-mcp)\n\nSearch 700+ DeFi vaults across Morpho, Aave, Yearn, Beefy, and Spark. Compare risk scores, analyze protocols, run due diligence &mdash; all through natural language.\n\n**No API key required. No installation needed.**\n\n[Quick Start](#quick-start) &bull; [Tools](#tools) &bull; [Example Prompts](#example-prompts) &bull; [Risk Framework](#risk-scoring) &bull; [Agent Skill](#agent-skill)\n\n</div>\n\n---\n\n## Why Philidor?\n\nMost DeFi data tools give you raw numbers. Philidor gives your AI agent **institutional-grade risk intelligence**.\n\n| Feature | Philidor | DefiLlama MCP | Generic DeFi APIs |\n|---|:---:|:---:|:---:|\n| Vault risk scores (0&ndash;10) | :white_check_mark: | :x: | :x: |\n| Risk vector decomposition | :white_check_mark: | :x: | :x: |\n| Vault comparison | :white_check_mark: | :x: | :x: |\n| Curator intelligence | :white_check_mark: | :x: | :x: |\n| Protocol security history | :white_check_mark: | :x: | Partial |\n| Due diligence prompts | :white_check_mark: | :x: | :x: |\n| Portfolio risk assessment | :white_check_mark: | :x: | :x: |\n| No API key needed | :white_check_mark: | :white_check_mark: | Varies |\n| Hosted (zero install) | :white_check_mark: | :x: | :x: |\n\n---\n\n## Quick Start\n\n### Remote Server (Recommended)\n\nConnect directly to the hosted server &mdash; zero installation, always up to date:\n\n```\nhttps://mcp.philidor.io/api/mcp\n```\n\n### Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"philidor\": {\n      \"url\": \"https://mcp.philidor.io/api/mcp\"\n    }\n  }\n}\n```\n\n### Claude Code\n\n```bash\nclaude mcp add philidor --transport http https://mcp.philidor.io/api/mcp\n```\n\n### Cursor\n\nAdd to `.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"philidor\": {\n      \"url\": \"https://mcp.philidor.io/api/mcp\"\n    }\n  }\n}\n```\n\n### Windsurf\n\nAdd to your MCP settings:\n\n```json\n{\n  \"mcpServers\": {\n    \"philidor\": {\n      \"serverUrl\": \"https://mcp.philidor.io/api/mcp\"\n    }\n  }\n}\n```\n\n### Docker (stdio)\n\n```bash\ndocker run -i --rm ghcr.io/philidor-labs/philidor-mcp\n```\n\n### Local (stdio)\n\n```bash\ngit clone https://github.com/Philidor-Labs/philidor-mcp.git\ncd philidor-mcp\nnpm install\nnpm start\n```\n\n---\n\n## Tools\n\n10 tools for vault discovery, risk analysis, and protocol research.\n\n### `search_vaults`\n\nSearch and filter DeFi vaults by chain, protocol, asset, risk tier, TVL, and more.\n\n| Parameter | Type | Description |\n|---|---|---|\n| `query` | string | Search by vault name, symbol, asset, protocol, or curator |\n| `chain` | string | Filter by chain (Ethereum, Base, Arbitrum, ...) |\n| `protocol` | string | Filter by protocol ID (morpho, aave-v3, yearn-v3, beefy, spark) |\n| `asset` | string | Filter by asset symbol (USDC, WETH, ...) |\n| `riskTier` | string | Filter by risk tier: Prime, Core, or Edge |\n| `minTvl` | number | Minimum TVL in USD |\n| `sortBy` | string | Sort field: tvl_usd, apr_net, name |\n| `sortOrder` | string | Sort order: asc or desc |\n| `limit` | number | Max results (default 10, max 50) |\n\n### `get_vault`\n\nGet detailed information about a specific vault including risk breakdown, recent events, and historical snapshots. Lookup by `id` or by `network` + `address`.\n\n| Parameter | Type | Description |\n|---|---|---|\n| `id` | string | Vault ID (e.g. `morpho-ethereum-0x...`) |\n| `network` | string | Network slug (ethereum, base, arbitrum) |\n| `address` | string | Vault contract address (0x...) |\n\n### `get_vault_risk_breakdown`\n\nDetailed breakdown of a vault's three risk vectors with sub-metrics: asset quality, platform code maturity, and governance controls. Returns dimension-level scores, caps, hard-fail flags, and overrides.\n\n| Parameter | Type | Description |\n|---|---|---|\n| `network` | string | Network slug |\n| `address` | string | Vault contract address |\n\n### `compare_vaults`\n\nSide-by-side comparison of 2&ndash;3 vaults on TVL, APR, risk score, risk tier, and audit status.\n\n| Parameter | Type | Description |\n|---|---|---|\n| `vaults` | array | Array of 2&ndash;3 objects with `network` and `address` |\n\n### `find_safest_vaults`\n\nFind the top 10 audited, high-confidence vaults sorted by risk score.\n\n| Parameter | Type | Description |\n|---|---|---|\n| `asset` | string | Filter by asset symbol |\n| `chain` | string | Filter by chain name |\n| `minTvl` | number | Minimum TVL in USD |\n\n### `get_protocol_info`\n\nProtocol details including TVL, vault count, versions, auditors, bug bounties, and security incidents.\n\n| Parameter | Type | Description |\n|---|---|---|\n| `protocolId` | string | Protocol ID (morpho, aave-v3, yearn-v3, beefy, spark) |\n\n### `get_curator_info`\n\nCurator details including managed vaults, TVL, chain distribution, and performance metrics.\n\n| Parameter | Type | Description |\n|---|---|---|\n| `curatorId` | string | Curator ID |\n\n### `get_market_overview`\n\nHigh-level DeFi vault market statistics: total TVL, vault count, risk distribution, and TVL by protocol. No parameters required.\n\n### `explain_risk_score`\n\nExplain what a specific risk score means, including the tier, calculation method, and thresholds.\n\n| Parameter | Type | Description |\n|---|---|---|\n| `score` | number | Risk score (0&ndash;10) |\n\n### `list_vaults_with_incidents`\n\nList all vaults that had a recent critical incident (last 365 days). Sorted by TVL descending, then by recency. No parameters required.\n\n---\n\n## Resources\n\n| URI | Description |\n|---|---|\n| `philidor://methodology` | The Vector Risk Framework v4.1 documentation |\n| `philidor://supported-chains` | Supported blockchain networks with vault counts |\n| `philidor://supported-protocols` | Supported DeFi protocols with TVL data |\n\n## Prompts\n\n| Prompt | Description |\n|---|---|\n| `vault_due_diligence` | Comprehensive due diligence report for a vault |\n| `portfolio_risk_assessment` | Portfolio-level risk analysis across positions |\n| `defi_yield_comparison` | Yield comparison with risk-adjusted analysis |\n\n---\n\n## Example Prompts\n\nOnce connected, try asking your AI assistant:\n\n**Discovery**\n\n> \"Find the safest USDC vaults with at least $10M TVL\"\n\n> \"What Morpho vaults are available on Base?\"\n\n> \"Show me the DeFi market overview\"\n\n**Analysis**\n\n> \"Run due diligence on the Steakhouse USDC vault on Ethereum\"\n\n> \"Compare the top 3 USDC vaults by risk score\"\n\n> \"What's the risk breakdown for this vault: ethereum/0x...\"\n\n**Portfolio**\n\n> \"Assess my portfolio: 50% in Morpho Steakhouse USDC, 30% in Aave USDC, 20% in Yearn USDC\"\n\n> \"Which protocols have had security incidents?\"\n\n> \"What does a risk score of 8.5 mean?\"\n\n---\n\n## Risk Scoring\n\nPhilidor uses the **Vector Risk Framework v4.1** to decompose vault risk into three measurable vectors:\n\n```\nFinal Score = 40% Asset + 40% Platform + 20% Governance\n```\n\n### Asset Composition (40%)\n\nQuality of underlying collateral. Blue-chip assets (ETH, USDC) score highest. Factors include oracle reliability, liquidity depth, and peg stability.\n\n### Platform Code (40%)\n\nCode maturity measured by:\n\n- **Lindy Score** &mdash; time-based safety (>2 years &asymp; 9/10)\n- **Audit Density** &mdash; number and quality of audits\n- **Dependency Risk** &mdash; multiplicative penalties for risky dependencies\n- **Incident Penalty** &mdash; caps score after security incidents\n\n### Governance (20%)\n\nExit window for users:\n\n| Control | Score |\n|---|---|\n| Immutable contract | 10/10 |\n| 7+ day timelock | 9/10 |\n| No timelock | 1/10 |\n\n### Risk Tiers\n\n| Tier | Score | Meaning |\n|---|---|---|\n| **Prime** | 8.0&ndash;10.0 | Institutional-grade &mdash; mature code, multiple audits, safe governance |\n| **Core** | 5.0&ndash;7.9 | Moderate safety &mdash; audited but newer or flexible governance |\n| **Edge** | 0.0&ndash;4.9 | Higher risk &mdash; requires careful due diligence |\n\n---\n\n## Architecture\n\n```\n┌──────────────────┐     ┌─────────────────┐     ┌──────────────┐\n│  Claude / Cursor  │────▶│  Philidor MCP   │────▶│ Philidor API │\n│  Windsurf / etc.  │◀────│  Server         │◀────│              │\n└──────────────────┘     └─────────────────┘     └──────┬───────┘\n                          10 tools, 3 resources,         │\n                          3 prompts                      │\n                                                   ┌────▼────┐\n                                                   │ On-chain │\n                                                   │  data    │\n                                                   └─────────┘\n```\n\n- **Transport**: Streamable HTTP (remote) or stdio (local/Docker)\n- **API**: Calls the [Philidor Public API](https://api.philidor.io/v1/docs) &mdash; no API key needed\n- **Stateless**: Fresh server instance per request, no session state\n- **Data**: 700+ vaults across Ethereum, Base, Arbitrum, Polygon, Optimism, and Avalanche\n\n---\n\n## Agent Skill\n\nInstall the Philidor MCP skill into your coding agent via [skills.sh](https://skills.sh):\n\n```bash\nnpx skills add philidor-labs/philidor-mcp\n```\n\nThis gives your agent full knowledge of all tools, resources, prompts, recommended workflows, and best practices for DeFi vault analysis.\n\n### Also Available\n\n| Interface | Description | Link |\n|---|---|---|\n| **CLI** | Terminal-based vault intelligence &mdash; scriptable, pipeable, agent-sandboxed | [philidor-cli](https://github.com/Philidor-Labs/philidor-cli) |\n| **OpenClaw Skill** | Skill definition for the OpenClaw agent platform | [npm](https://www.npmjs.com/package/@philidorlabs/openclaw-skill) |\n\n---\n\n## Supported Protocols\n\nMorpho, Aave v3, Yearn v3, Beefy, Spark &mdash; with more being added regularly.\n\nSee the full list at [app.philidor.io](https://app.philidor.io).\n\n---\n\n## Development\n\n```bash\ngit clone https://github.com/Philidor-Labs/philidor-mcp.git\ncd philidor-mcp\nnpm install\nnpm start\n```\n\nThe server connects to the public Philidor API by default. To use a custom endpoint:\n\n```bash\nPHILIDOR_API_URL=http://localhost:3003 npm start\n```\n\n---\n\n## Links\n\n- [Philidor Analytics](https://app.philidor.io) &mdash; explore vaults and risk scores\n- [Philidor CLI](https://github.com/Philidor-Labs/philidor-cli) &mdash; terminal-based vault intelligence\n- [API Documentation](https://api.philidor.io/v1/docs) &mdash; OpenAPI/Swagger docs\n- [Risk Methodology](https://app.philidor.io/methodology) &mdash; how scores are calculated\n- [Smithery](https://smithery.ai/servers/philidor/defi) &mdash; MCP server registry\n- [Twitter](https://twitter.com/philidorlabs) &mdash; updates and announcements\n\n## License\n\n[MIT](LICENSE)\n",
  "bytes": 11120,
  "sha": "538d4295748f4f9ef53b4913f74ca4a6c080749e2391bc0ad64fbba1e8f5a515",
  "repo_slug": "philidor-labs/philidor-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_philidor_defi_vaults_bc16edb9/readme"
}