UncalledBook a demo

Know when AI agents stop calling your MCP tools.

Daily checks in Claude, Cursor, ChatGPT and Codex. When your tool stops getting called, you know, and you know why.

Measured from the agent's side, not from your logs. Your server is never called.

Who calls track_order

MCP analytics · acme-shop-mcp · last 14 days · demo data

Share of runs in which each agent called track_order over the last 14 days, with the cause of each drop
AgentNowWhy
ClaudeOpus 5.531%CauseClaude app update
ChatGPTGPT-5.534%CauseModel update
CursorSonnet 5.538%CauseYour release v2.4
CodexGPT-5.5-Codex76%Steady
Gemini3.1 Pro77%Steady
The whole story in 15 seconds. Demo data: acme-shop-mcp is made up.

You only see the calls agents make. Never the ones they skip.

No error. No log line. Your server just gets quieter.

Watch both screens: the agent looks through what it has, finds nothing, and asks the customer which shop it was. Your tool, in red, was right there.

Real claude.ai and ChatGPT runs. The red marker is staged: acme-shop-mcp is made up. Not affiliated with Anthropic or OpenAI.

How it works

  1. Paste your MCP server URL.

    We read its tool list and build a stand-in. Your server is never called.

  2. Add the prompts your users type.

    Every day we run them in each agent: Claude, Cursor, ChatGPT, Codex and Gemini.

  3. See the call rate per agent.

    When it drops, you get an alert with the cause (your release, the model, or the agent’s update) and a suggested fix.

Demo data.

Free while we build it with the first teams.

Pro from $149 a month at launch. Reserve the early-access price now; nothing to pay today.

No payment now. No card. One email when the price goes live.

Questions

Does Uncalled call my MCP server?

No. It reads your tool list once and builds a stand-in from it, so no test traffic ever reaches your server.

Which agents does it check?

Claude, Cursor, ChatGPT, Codex and Gemini at launch. Each one is run with the prompts your users type, every day.

What makes an agent stop calling a tool?

Three things, mostly: your own release changed the tool description or schema; a new model version weighs tools differently; or the agent app updated its built-in tools or prompts. Uncalled checks all three and names the one that matches.

How is this different from logging tool calls, like MCPcat or PostHog?

Logs show the calls that reached your server. Uncalled shows the ones that never happened, per agent, with the cause.

Who is behind it, and what does it cost?

One founder, building it with the first teams. Free during early access; Pro is planned from $149 a month at launch. Write to hello@uncalled.app.

Find out whether agents still call your tool.

Twenty minutes on Google Meet. Bring your MCP server if you have one.

Book a 20-min demo