INDIVIDUAL MCP TOOL

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.

youraitools.conone authenticationAvailability not checked

LIVE ENDPOINT

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

No auth detected

Connect to this endpoint to inspect the live schema for watch_mcp_server and invoke it with your own arguments.

{}

Potential side effects detected · medium confidence · heuristic, not a guarantee.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.toolfit]
url = "https://api.youraitools.co/toolfit/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "toolfit": {
      "type": "http",
      "url": "https://api.youraitools.co/toolfit/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: toolfit
Remote MCP URL: https://api.youraitools.co/toolfit/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "toolfit": {
      "url": "https://api.youraitools.co/toolfit/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "toolfit": {
      "type": "http",
      "url": "https://api.youraitools.co/toolfit/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "toolfit",
  "transport": "streamable-http",
  "url": "https://api.youraitools.co/toolfit/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

audit_tools — 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.
diff_tools — What changed in a tool list since you approved it?
check_mcp_server — Does this remote MCP server work, and is it worth connecting or paying for?
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.
watch_cancel — Free: cancel a watch (no further checks or webhooks; not refunded).