---
title: Let agents read their own telemetry
description: The ClawMetry MCP server gives Claude Code, Cursor and any MCP client their own session history, cost and traces — so a coding agent can diagnose itself.
keywords: MCP server agent telemetry, Claude Code self diagnosis, agent memory of past sessions, MCP observability, agent introspection
eyebrow: Agents & MCP
---

# Let agents read their own telemetry

Your coding agent has no memory of yesterday. It cannot tell you what it worked
on last week, whether it has hit this error before, what its last attempt at
this migration cost, or that it is currently repeating a session that already
failed.

ClawMetry has all of that. The MCP server hands it over.

```bash
claude mcp add clawmetry -- clawmetry mcp
```

Now the agent can ask.

> **You:** Before you start, check clawmetry — have I tried this migration
> before?
>
> **Claude:** I found two sessions touching `migrations/0042`. The one on the
> 2nd ran 38 tool calls and ended with the same `IntegrityError` you are
> describing; the one on the 4th cost $6.10 and was stopped after a repeated
> tool failure on `alembic upgrade`. In both, the failure follows a
> `psql -c "\d users"` that returned an empty result. Let me check the schema
> first this time.

That is not a summary of the conversation you are in. It is your own telemetry,
read by the agent, before it starts spending money repeating itself.

## Why this is different from a dashboard

A dashboard answers questions you thought to ask. An agent with access to its
own history answers questions *in the middle of doing the work*, when the answer
changes what it does next:

- **"Have I seen this error?"** — asked before debugging, not after.
- **"Am I looping?"** — an agent that can count its own repeated tool calls can
  stop itself.
- **"What did the last attempt cost?"** — the difference between trying a
  cheaper approach and burning the same $40 again.
- **"Which of my runtimes is the expensive one?"** — a question about your
  fleet, answered inside the tool you are already in.
- **"What changed since the last successful run?"** — the transcript of the run
  that worked is right there.

## What it exposes

Five tools, over stdio, locally:

| Tool | Question |
|---|---|
| `list_sessions` | What have I been running? |
| `get_cost_summary` | What did it cost over this window? |
| `get_session_trace` | What happened inside one session? |
| `list_events` | Raw events, filtered by session, type or time |
| `get_health` | Is ClawMetry itself healthy? |

→ [MCP tool reference](/docs/mcp/tools/)

Those five cover a surprising amount, because `list_events` takes an event-type
filter and `get_session_trace` returns the full tool stream. "Show me every
`tool_result` with an error in the last day" is one call.

## It reads across runtimes

This is the part people miss. The MCP server does not read Claude Code's
transcripts — it reads **ClawMetry's store**, which holds every runtime on the
machine.

So Claude Code can answer questions about your Cursor sessions. Codex can look
at what the OpenClaw agent did overnight. A local agent can compare its own
cost per task against the hosted one.

→ [Cross-runtime questions](/docs/mcp/cross-runtime/)

## Safety and shape

- **Local only.** The transport is stdio; the data path is a loopback HTTP call
  to the daemon with a token from a file only your user can read. Nothing about
  MCP opens a network surface.
- **Read only.** There is no tool here that writes, deletes, or controls an
  agent. An agent with this server attached cannot pause another agent, change a
  policy, or modify your store.
- **Honest when empty.** With no daemon running, tools return an explicit
  "daemon is not running" error rather than an empty list — because an empty list
  reads as "you did nothing this week" and an agent will believe it.
- **It sees your transcripts.** That is the point, and it is worth being
  deliberate about: an agent with this attached can read the content of past
  sessions, including any secrets that ended up in them. See
  [Hardening](/docs/config/security/) for redaction.

## Getting started

1. [Connect the MCP server](/docs/mcp/install/) to your client
2. Try the [self-diagnosis recipes](/docs/mcp/self-diagnosis/)
3. Turn the good ones into [skills and prompts](/docs/mcp/skills/)