What is philidor-api-handoff?

A guide for deciding when to use Philidor's free read-only data connection and when to use its separate API documentation. An API is a service that software calls to request data.

Use it to handle questions about vaults, markets, incidents, risk explanations, and other Philidor data, or to direct users to the API for unavailable information.

It prevents unsupported figures from being filled in through guesswork and identifies requests that the free connection does not cover, such as bulk scores or richer risk data.

philidor-api-handoff — Skill for Cursor by Philidor-Labs/philidor-mcp

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Philidor-Labs/philidor-mcp --skill philidor-api-handoff

Clone the repo

git clone --depth 1 https://github.com/Philidor-Labs/philidor-mcp

Made for: Cursor.

Or install philidor, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/philidor-labs/philidor-mcp/philidor-api-handoff/github.svg)](https://agentmods.dev/skills/philidor-labs/philidor-mcp/philidor-api-handoff)

Your own site

<a href="https://agentmods.dev/skills/philidor-labs/philidor-mcp/philidor-api-handoff"><img src="https://agentmods.dev/badge/skills/philidor-labs/philidor-mcp/philidor-api-handoff/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/philidor-labs/philidor-mcp/philidor-api-handoff"><img src="https://agentmods.dev/badge/skills/philidor-labs/philidor-mcp/philidor-api-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 931 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.00931
Opus 5.5	$0.00026	$0.00372
Sonnet 5.5	$0.00013	$0.00186
Haiku 4.5	$0.00006	$0.00093

Measured 16d ago against content hash 97a222e13a07, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

philidor-api-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/philidor-api-handoff/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to leave the free MCP for the Philidor API

The Cursor plugin talks to https://mcp.philidor.io/api/mcp with no API key. That server is read-only and currently exposes these tools: search_vaults, get_vault, get_vault_risk_breakdown, list_markets, get_market, get_market_events, check_loop_venue, compare_vaults, find_safest_vaults, get_protocol_info, get_curator_info, get_market_overview, explain_risk_score, list_vaults_with_incidents. Resources: philidor://methodology, philidor://supported-chains, philidor://supported-protocols. Prompts: vault_due_diligence, portfolio_risk_assessment, defi_yield_comparison, review_loop_venue.

If the question is answered by one of those, stay on MCP. Do not browse api.philidor.io to fill a number a tool should have returned, and do not fabricate the missing figure.

Stay on MCP

Vault search, one vault, vector breakdown, compare, safest-vault screen, curator, protocol, platform overview.
Lending market list, one market, market events, loop-venue underwriting.
Score explanation and the 365-day critical vault-incident list.
Wallet health factor and unsigned transactions are not the Philidor API either. Hand those to the protocol MCP (Aave is https://mcp.aave.com) after check_loop_venue.

Point at the API

Send the user to the docs instead of calling plan-gated routes yourself. Base URL https://api.philidor.io. Access model: API Access and Plans. Per-route plan: Access Matrix. Commercial packaging: philidor.io/pricing.

Do not quote a dollar price. Do not name a plan that is not in those pages. As of the access doc, issued keys are data, decisioning, or embedded:

Data — the doc lists this key for /v1/baskets/*, /v1/oracle-vector/*, /v1/assets/enriched and /v1/assets/enriched/facets, /v1/vaults/scores, /v1/vaults/changes, /v1/events/stream, /v1/stats/history, /v1/stats/rating-dynamics, and per-vault /holders, /holders/history, /markets, /strategies, and /strategy.
Decisioning — the doc says this adds the Risk Graph family (portfolio look-through, pre-trade checks with signed decisions, breach and incident exposure) and signed webhooks. The Risk Graph API is in limited release and is enabled by arrangement. Public decision verification stays available without a key when that API is enabled.
Embedded — the doc describes custom integrations, white-label data, contractual terms, custom webhooks, and custom limits.

Read the full file on GitHub · 42 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

16d ago First seen · 42 lines · 64 tokens per session scan A 97a222e13a07

Subscribe to this mod's changes

philidor-api-handoff is a skill published in the GitHub repository Philidor-Labs/philidor-mcp (5 stars, last pushed 16d ago), licensed MIT. It adds 64 tokens to every session and 931 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-01.

Finance and fintech Web3 and blockchain aave ai-tools claude crypto defi ethereum

philidor-api-handoff

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

When to leave the free MCP for the Philidor API

Stay on MCP

Point at the API

What this file has done since we first saw it

Other skills, from other repositories

trading-solana

pump-swarm

copy-trading

trading-evm

whale-tracking

acp