ToolFit + MCPCheck

Working · 70 ms

co.youraitools/toolfitv0.1.1 Domain verified

Audit, pin and diff agent tool lists; preflight and watch remote MCP servers. Free tier; x402.

AI & Agents

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://api.youraitools.co/toolfit/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

audit_tools Read-only

Check the tool definitions an agent loads, before they cost tokens or fail: estimated tokens per tool, schema errors per provider (OpenAI, Anthropic, Gemini, Bedrock, MCP; add openai_strict for strict mode) with JSON paths and fixed definitions, tool pairs models will confuse with fix hints, basic poisoning patterns, a grade and a pin (set_id) for diff_tools. Pass "tools" (array in any common format) or "url" (public remote MCP server; tools are listed, never called). level "lite" returns the summary only. Free: 20 calls/day per IP (shared with diff_tools), then $0.003 lite / $0.01 full via x402 or credits.

urlstring

Public remote MCP server URL (Streamable HTTP, https), e.g. https://api.youraitools.co/mcp/hub. ToolFit only lists its tools.

levelstring

lite = summary only; full (default) = every issue, fixed definitions, pair hints

toolsarray

Tool definitions: MCP tools/list entries, OpenAI {type:"function",function:{...}}, Anthropic {name,description,input_schema}, Gemini functionDeclarations or Bedrock toolSpec. Max 500.

providersarray

Providers to check (default openai, anthropic, gemini, bedrock, mcp; add openai_strict for Structured Outputs strict mode). GET: comma list.

Tools (6)

audit_tools

read-only

Argument	Type	Description
url	string	Public remote MCP server URL (Streamable HTTP, https), e.g. https://api.youraitools.co/mcp/hub. ToolFit only lists its tools.
level	string	lite = summary only; full (default) = every issue, fixed definitions, pair hints
tools	array	Tool definitions: MCP tools/list entries, OpenAI {type:"function",function:{...}}, Anthropic {name,description,input_schema}, Gemini functionDeclarations or Bedrock toolSpec. Max 500.
providers	array	Providers to check (default openai, anthropic, gemini, bedrock, mcp; add openai_strict for Structured Outputs strict mode). GET: comma list.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public remote MCP server URL (Streamable HTTP, https), e.g. https://api.youraitools.co/mcp/hub. ToolFit only lists its tools."
    },
    "level": {
      "enum": [
        "lite",
        "full"
      ],
      "type": "string",
      "description": "lite = summary only; full (default) = every issue, fixed definitions, pair hints"
    },
    "tools": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Tool definitions: MCP tools/list entries, OpenAI {type:\"function\",function:{...}}, Anthropic {name,description,input_schema}, Gemini functionDeclarations or Bedrock toolSpec. Max 500."
    },
    "providers": {
      "type": "array",
      "items": {
        "enum": [
          "openai",
          "openai_strict",
          "anthropic",
          "gemini",
          "bedrock",
          "mcp"
        ],
        "type": "string"
      },
      "description": "Providers to check (default openai, anthropic, gemini, bedrock, mcp; add openai_strict for Structured Outputs strict mode). GET: comma list."
    }
  }
}

check_mcp_server

Does this remote MCP server work, and is it worth connecting or paying for? Sends initialize and tools/list only (never calls a tool) and reports reachability, protocol version, sign-in method (OAuth protected-resource metadata), x402 payment terms if it asks for payment, latency, tool count and token cost, provider compatibility, poisoning patterns in tools and server instructions, issues and a grade A-F, plus a pin for later diffs. https public hosts only. Free: 10 checks/day per IP, then $0.005 via x402 or credits.

read-only

Argument	Type	Description
url*	string	Public remote MCP server URL (Streamable HTTP, https), e.g. https://api.youraitools.co/mcp/hub. ToolFit only lists its tools.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Public remote MCP server URL (Streamable HTTP, https), e.g. https://api.youraitools.co/mcp/hub. ToolFit only lists its tools."
    }
  }
}

diff_tools

What changed in a tool list since you approved it? Compares "tools" or "url" now with "pin" (set_id from audit_tools/diff_tools) or "baseline" (earlier definitions). Each change is labeled breaking (removed tool or param, new required param, type or enum removal), suspicious (new text with injection patterns or hidden characters), review (description, title, annotation or new tool) or additive; descriptions come with before/after text and a word diff. Returns a new pin. Free: 20 calls/day per IP (shared with audit_tools), then $0.002 via x402 or credits.

read-only

Argument	Type	Description
pin	string	A pin (set_id "ts_..." from an earlier ToolFit call) to compare against.
url	string	Public remote MCP server URL (Streamable HTTP, https), e.g. https://api.youraitools.co/mcp/hub. ToolFit only lists its tools.
tools	array	Tool definitions: MCP tools/list entries, OpenAI {type:"function",function:{...}}, Anthropic {name,description,input_schema}, Gemini functionDeclarations or Bedrock toolSpec. Max 500.
baseline	array	Instead of pin: the earlier tool definitions themselves.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "pin": {
      "type": "string",
      "description": "A pin (set_id \"ts_...\" from an earlier ToolFit call) to compare against."
    },
    "url": {
      "type": "string",
      "description": "Public remote MCP server URL (Streamable HTTP, https), e.g. https://api.youraitools.co/mcp/hub. ToolFit only lists its tools."
    },
    "tools": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Tool definitions: MCP tools/list entries, OpenAI {type:\"function\",function:{...}}, Anthropic {name,description,input_schema}, Gemini functionDeclarations or Bedrock toolSpec. Max 500."
    },
    "baseline": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Instead of pin: the earlier tool definitions themselves."
    }
  }
}

watch_cancel

Free: cancel a watch (no further checks or webhooks; not refunded). Needs watch_id and the secret returned when it was created.

destructive

Argument	Type	Description
secret*	string	The whsec_... secret returned once when the watch was created
watch_id*	string	watch_id (w_...) returned by POST /v1/watch

Input schema (JSON)

{
  "type": "object",
  "required": [
    "watch_id",
    "secret"
  ],
  "properties": {
    "secret": {
      "type": "string",
      "description": "The whsec_... secret returned once when the watch was created"
    },
    "watch_id": {
      "type": "string",
      "description": "watch_id (w_...) returned by POST /v1/watch"
    }
  }
}

watch_mcp_server

Hosted watch (paid only; this MCP call validates and returns how to pay): ToolFit re-audits a public remote MCP server every 24 h ($0.25) or 6 h ($0.60) for 30 days and POSTs an HMAC-SHA256 signed JSON webhook to your https endpoint when its tools/list fingerprint or grade changes, or it goes unreachable or recovers. Pay at POST /v1/watch or /v1/watch/6h with x402 or a credits key; the response has watch_id and the signing secret (shown once).

Argument	Type	Description
url*	string	Public remote MCP server URL (Streamable HTTP, https), e.g. https://api.youraitools.co/mcp/hub. ToolFit only lists its tools.
every	string	Check interval: 24h (default, $0.25 per 30 days) or 6h ($0.60 per 30 days).
webhook*	string	Your https endpoint (public host, port 443) that receives the signed JSON change notifications. A query string is allowed.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "url",
    "webhook"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Public remote MCP server URL (Streamable HTTP, https), e.g. https://api.youraitools.co/mcp/hub. ToolFit only lists its tools."
    },
    "every": {
      "enum": [
        "24h",
        "6h"
      ],
      "type": "string",
      "description": "Check interval: 24h (default, $0.25 per 30 days) or 6h ($0.60 per 30 days)."
    },
    "webhook": {
      "type": "string",
      "description": "Your https endpoint (public host, port 443) that receives the signed JSON change notifications. A query string is allowed."
    }
  }
}

watch_status

Free: state (active, expired, cancelled), interval, expiry, next check, last result (pin, grade, score, tool count) and webhook delivery counters for a watch. Needs watch_id and the secret returned when it was created.

read-only

Argument	Type	Description
secret*	string	The whsec_... secret returned once when the watch was created
watch_id*	string	watch_id (w_...) returned by POST /v1/watch

Input schema (JSON)

{
  "type": "object",
  "required": [
    "watch_id",
    "secret"
  ],
  "properties": {
    "secret": {
      "type": "string",
      "description": "The whsec_... secret returned once when the watch was created"
    },
    "watch_id": {
      "type": "string",
      "description": "watch_id (w_...) returned by POST /v1/watch"
    }
  }
}