{"uid":"cap_ZVUHxij6K1krV37M2cjj0","slug":"preflight-checker-mcp-server-safety-audit-0a894951","name":"PreFlight Checker — MCP Server Safety Audit","description":"MCP server safety audit: completes a real initialize+tools/list handshake, then statically scans every tool's name/description/schema for hidden unicode (tool-poisoning), prompt-injection-style phrasing, and tools that quietly combine multiple high-privilege capabilities (network+filesystem+exec+credential access). If a GitHub repo is supplied, folds in a real software-supply-chain signal too.","url":"https://x402-api-catalog.onrender.com/api/mcp-audit","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"base URL of the MCP server (streamable-HTTP transport)"},"repo":{"type":"string","description":"optional owner/repo to fold in a GitHub supply-chain signal"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"url":{"type":"string"},"score":{"type":"number"},"verdict":{"type":"string"}}}}}}},"responseSchema":{"type":"json","example":{"url":"https://mcp.example.com/mcp","score":90,"verdict":"healthy: no red flags found","findings":[],"tools_found":3}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.06","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.06/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.06","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.06","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_sQEpF-h_9K12aLyGrPa4C","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.06","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Performs a live MCP handshake plus static analysis of every tool's name, description, and schema to detect tool-poisoning, prompt injection, and dangerous capability combinations, with optional GitHub supply-chain signal.","exampleAgentPrompt":"Can you run a full safety audit on this MCP server at https://my-mcp-server.example.com — check for prompt injection, tool poisoning, hidden unicode, and dangerous capability combos? Also fold in a supply-chain check for my-org/my-repo while you're at it.","exampleUseCases":[{"title":"Vetting a third-party MCP server","prompt":"Before I connect our agent to this MCP server at https://partner-tools.example.com, can you audit it for hidden unicode, prompt injection tricks in the tool descriptions, and any tools that quietly bundle network, filesystem, and credential access together?"},{"title":"Pre-deployment security check with GitHub signal","prompt":"We're about to deploy an agent that uses https://open-source-mcp.example.com — can you run a security scan on it and also check the GitHub repo opensourcecorp/mcp-tools for any supply-chain red flags?"},{"title":"Continuous trust monitoring for MCP toolchain","prompt":"I want to know if the MCP server at https://internal-tools.mycompany.com is still clean — scan it for tool-poisoning attacks or any new prompt-injection-style phrasing that might have snuck into the tool schemas since last time."}],"resultDescription":"Returns a safety score, a verdict (e.g. pass/warn/fail), and detailed findings including any detected hidden unicode characters, prompt-injection-style phrasing in tool names or descriptions, tools that combine multiple high-privilege capabilities (network, filesystem, exec, credential access), and optionally a GitHub supply-chain signal for the linked repository.","failureModes":["MCP server URL unreachable or not responding to initialize handshake — audit fails with connection error","Target server does not speak streamable-HTTP MCP transport — handshake fails","GitHub repo not found or rate-limited — supply-chain signal omitted from results","Malformed URL input — returns validation error","Server times out during tools/list enumeration — partial results or error returned"],"whenToPreferThis":"Use this endpoint when you need to vet an MCP server before connecting an AI agent to it, especially when the server is third-party, open-source, or untrusted. It is the right choice over generic HTTP health checks because it performs a real MCP protocol handshake and specifically targets AI-agent attack vectors: tool poisoning, hidden unicode, prompt injection in schemas, and dangerous capability bundling. If you also have a GitHub repository for the MCP server, pass it to get a software supply-chain risk signal in the same call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:43:18.109Z","isFirstParty":false}