Philidor MCP
Hosted MCP scoring risk across 700+ DeFi vaults on Morpho, Aave, Spark, Yearn, and Beefy for agent due diligence.
- Sato Score76
- ChainsEthereum, Base +4
Philidor MCP is an open-source MCP server by Philidor Labs on Ethereum, Base, Arbitrum and other chains, with last code activity on 2026-03-02 (Quiet). Latest release on 2026-02-22. Sato Score 76/100 (how open, active and verifiable it is, not a safety grade), as of 2026-10-15. How the score works →
See how to install Philidor MCP →Last commit Mar 2, 2026 · Last release Feb 22, 2026 · ★ 4
Listed from github.com/Philidor-Labs/philidor-mcp on 2026-07-12. Install: not attempted. Evidence →
Next step
Watch Philidor MCP
One email if what we observe changes — its repo goes quiet or disappears, or the listing is retired. Nothing else.
Check it from your agent
Add Sato Hub’s MCP server (no key), then ask:
https://satohub.ai/api/mcpRun Sato Hub Preflight on philidor-labs/philidor-mcp before I use it.Your project?
Prove you control the domain and correct this page — description, links, tags, chains. A claim proves control, not verification: it never changes the Sato Score.
Claim this listing →Overview
Philidor MCP exposes 10 tools for searching, comparing, and scoring DeFi vaults across Morpho, Aave v3, Spark, Yearn v3, and Beefy. Risk scores decompose into asset composition, platform code maturity, and governance controls per its published Vector Risk Framework v4.1. Run by Philidor Labs; hosted with no API key required, so a builder can plug it straight into an agent's due-diligence or allocation loop.
Sato Score
76/100· HighHow open, active & verifiable — not a safety or returns grade.
- Maintenance & liveness
- 35/35
- Code transparency
- 17/20
- Interface verifiability
- 10/10
- Docs & demo
- 0/10
- Listing transparency & provenance
- 11/15
- Independent verification
- 3/10
Live endpoint probed — we called the hosted MCP endpoint and it answered with its real tool inventory (proves the interface works, not runtime safety).
Evidence — listed vs checked · what the words mean
Listed from github.com/Philidor-Labs/philidor-mcp on 2026-07-12. Install: not attempted.
| Claim | Value | Evidence | Source | Checked |
|---|---|---|---|---|
| Chains supported | Ethereum, Base, Arbitrum, Polygon, Optimism, Avalanche | self-reported | github.com/Philidor-Labs/philidor-mcp | as of 2026-10-15 |
| Verification status | Self-Reported — not independently reviewed | self-reported | github.com/Philidor-Labs/philidor-mcp | as of 2026-10-15 |
| Recent activity | last release 2026-02-22 · last commit 2026-03-02 | observed | github.com/Philidor-Labs/philidor-mcp | 2026-10-15 |
| Install works | documented by the project, not run by Sato Hubnot attempted by Sato Hub | self-reported | github.com/Philidor-Labs/philidor-mcp | as of 2026-07-14 |
| MCP endpoint answers | answered — 14 tools listed | observed | mcp.philidor.io | 2026-10-15 |
| Daily check record | 90 of 90 daily checks since 2026-07-17 succeededa success rate of our checks, not uptime; the source is this listing's own history | observed | — | 2026-10-14 |
| Deploys as | Hosted API, Docker, npmconfidence 0.85 | self-reported | github.com/Philidor-Labs/philidor-mcp | as of 2026-07-14 |
| Works with | Claude Desktop, Claude Code, Cursor, Windsurfconfidence 0.85 | self-reported | github.com/Philidor-Labs/philidor-mcp | as of 2026-07-14 |
| Sato Score | 76/100 (High)how open, active and verifiable — not a safety or quality grade | computed | satohub.ai | 2026-10-15 |
Self-reported rows are the project’s own words, dated when we recorded them — not a check. Only reproduced and reviewed rows carry a mark. None of these rows is a safety or quality rating.
Install — as documented by the project, not run by us
Runtime: remote
claude mcp add philidor --transport http https://mcp.philidor.io/api/mcp
{"mcpServers": {"philidor": {"url": "https://mcp.philidor.io/api/mcp"}}}claude mcp add --transport http satohub-philidor-mcp https://mcp.philidor.io/api/mcp
A remote server: your client connects to the project's endpoint. Installing runs third-party software under your own credentials. Sato Hub publishes the documented invocation and, where the harness reproduced it, the date it did — neither is a safety review.
Read from the project’s own docs as of 2026-07-14. What a deploy spec is →
Tool inventory — 14 tools, probed live 2026-10-15
search_vaults— Search and filter DeFi vaults by chain, protocol, asset, risk tier, TVL, and more. Returns a paginated list with risk scores and APR.get_vault— Get detailed information about a specific DeFi vault including risk breakdown, recent events, and historical snapshots. Lookup by ID or by network + address.get_vault_risk_breakdown— Get a detailed breakdown of a vault's risk vectors: Asset Composition, Platform and Strategy, Control and Governance, and History scores with sub-metrics.list_markets— List lending markets: the market a depositor actually picks (Aave/Spark pool, Aave V4 spoke, Compound Comet, Morpho Blue pair, or Kamino K-Lend market). Aave V4 spokes that share a liquidity hub are gget_market— Get one lending market with every reserve it contains: supplied, supply APR, borrowed, borrow APR, utilization and risk tier per reserve. Spoke ids look like aave-v4-10-etherfi-cash. Aave V4 hub parenget_market_events— Published risk events for ONE lending market: incidents, bad debt, liquidation cascades (e.g. mass liquidations on a Morpho Blue market). Market ids look like morpho-v1-1-pt-reusd-10dec2026-usdc-91-5.check_loop_venue— Underwrite a collateral/debt loop on ONE lending market: score, tier, utilization, borrow APR, deposit status, and recent incidents for both reserves. Does not compute health factor and does not prepacompare_vaults— Compare 2-3 DeFi vaults side-by-side on TVL, APR, risk score, risk tier, audited status, and more.find_safest_vaults— Find the highest risk-scored DeFi vaults, optionally filtered by asset, chain, or minimum TVL. Returns the top 10 audited vaults sorted by Philidor risk score (higher = lower assessed risk; scores areget_protocol_info— Get detailed information about a DeFi protocol including TVL, vault count, versions, auditors, and security incidents.get_curator_info— Get detailed information about a vault curator including their managed vaults, TVL, chain distribution, and performance.get_market_overview— Get a high-level overview of the DeFi vault market: total TVL, vault count, risk distribution, and TVL by protocol.explain_risk_score— Explain what a Philidor risk score means, including the tier (Prime/Core/Edge), how it is calculated, and what the thresholds are.list_vaults_with_incidents— List all vaults that had a recent critical incident (last 365 days). Critical = severity Critical or incident_severity major. Results are sorted by TVL descending, then by time since event ascending (
- Answers a handshake
- yes · 2026-10-15
- Answers a call
- yes — search_vaults returned in 1558 ms
Live probe verifies the interface responds — not what the tools do, their safety, or their output quality. The call is one read-only tool named by this server's own list (list_/get_/search_, no mutating verb anywhere in the name, no required arguments and none that look like a key, an address or an amount), asked once a day with no arguments. Not asked is not a failure.
Observed record — 91 daily checks since 2026-07-17
- Succeeded
- 91
- Failed
- 0
- Their error
- 0
- Unattributed
- 0
This is the share of our daily checks that succeeded — not an availability guarantee. A check can fail because the host was down, because our runner timed out, or because the network in between dropped it, and only the first of those is a fact about this project. Failures are split by what we can attribute; anything we cannot attribute is counted, not hidden. 46 of these checks predate 2026-09-01, when the probe counted a bot-block (HTTP 403) as a failure and recorded no reason for any failure. Every one of them passed, so the rate covers them too.
Last 30 days — to 2026-10-15, one point per UTC day
A gap is a day we have no attributable observation — never a zero. Thirty points is the whole shape the free layer carries; the daily rows behind it stay in the snapshot series.
Tool inventory history — 14 now, peak 14, since 2026-07-17
- 2026-09-13 13 → 14 +1 (check_loop_venue)
- 2026-08-26 12 → 13 +1 (get_market_events)
- 2026-08-24 10 → 12 +2 (get_market, list_markets)
Recorded from our own daily tools/list handshake. A shrinking toolset is a real signal for an agent choosing a server; a gap in the series means the probe did not succeed that day, not that the tools disappeared.
Details
- Chains
- Ethereum, Base, Arbitrum, Polygon, Optimism, Avalanche
- Agent types
- MCP Server, Data Provider
- Open source
- Yes
- Deploys as
- Hosted API, Docker, npm
- Works with
- Claude Desktop, Claude Code, Cursor, Windsurf
- Last checked
- 2026-10-15
Marketplace Signals
No marketplace signals recorded for this resource yet.
Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.
Where Philidor MCP fits
Related concepts: How Agents Interact With Smart Contracts, How Agents Use Wallets, What Are MCPs? The Standard Way to Give Agents Tools
Listing History
Recorded changes to Philidor MCP's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.
- Jul 18, 2026Sato Hub began tracking this listing
- Jul 14, 2026Edited: mcp endpoint url
- Jul 14, 2026Auto-enriched: deployment options, supported integrations
- Jul 13, 2026Listed on Sato Hub
Compared with
Appears in
- Onchain trading tools on Base, scored →
- Base MCP servers, scored →
- Ethereum MCP servers, scored →
- Hosted MCP endpoints answering today, scored →
- Base MCP servers you can use without a local server →
- MCP: the tool interface for agents →
- Onchain agents on Base →
- Onchain agents on Ethereum →
- Onchain agents on Arbitrum →
- Onchain agents on Polygon →
- Onchain agents on Optimism →
- Onchain agents on Avalanche →
Related Resources
Solana Agent Kit
ActiveSendAI's open-source toolkit connecting AI agents to Solana protocol actions.
Zerion
ActiveWallet and DeFi data provider offering portfolio, positions, transactions, PnL, and prices across many chains, with an agent-accessible API.
Bankr
ActiveCrypto execution layer and cross-chain wallet that lets agents and users trade, bridge, and manage assets via natural language, plus a skills marketplace and an x402 cloud for spinning up pay-per-call agent endpoints.
Reference
QuestionsWhat people ask about this pageShowHide
Questions people ask about Philidor MCP
- Is Philidor MCP open source?
- Yes. Philidor MCP is open source under the MIT license; the repository is https://github.com/Philidor-Labs/philidor-mcp. Checked as of 2026-10-15.
- Which chains does Philidor MCP support?
- Philidor MCP lists support for Ethereum, Base, Arbitrum, Polygon, Optimism, Avalanche as of 2026-10-15.
- Is Philidor MCP still maintained?
- The most recent code activity Sato Hub observed was on 2026-03-02 (last commit 2026-03-02, last release 2026-02-22), which Sato Hub labels "Quiet". Posts on X are not counted as maintenance. Activity is a recency signal, not a quality judgment.
- How do I install or run Philidor MCP?
- remote. Install: claude mcp add philidor --transport http https://mcp.philidor.io/api/mcp. Entry: {"mcpServers": {"philidor": {"url": "https://mcp.philidor.io/api/mcp"}}}. This is taken from the project's own documentation and has not been reproduced by Sato Hub. It runs as an MCP server (https://mcp.philidor.io/api/mcp).
- Is Philidor MCP verified on Sato Hub?
- Sato Hub holds one earned check for Philidor MCP: Live endpoint probed — we called the hosted MCP endpoint and it answered with its real tool inventory (proves the interface works, not runtime safety). Its Sato Score is 76 of 100, a measure of how open, active and verifiable the project is, not a safety, quality or returns grade.
Cite this pagePlain text, APA or BibTeXShowHide
Cite this page
Sato Hub. "Philidor MCP — Sato Hub." Sato Hub, updated 2026-10-15, accessed 2026-10-15. https://satohub.ai/resources/philidor-mcpData last refreshed 2026-10-15; this page is rebuilt daily. Citations carry the date so a reader can tell which snapshot a claim came from. Catalog data is licensed CC-BY-4.0.
Join the Sato Hub Briefing
Sign up for the Briefing: the agents, tools, and infrastructure that actually shipped, and why they matter.