# Your work board (`mttr_todo`)

Updated October 24, 2026.

## What does mttr_todo do?

Your work across every site you have claimed, as your progress page shows it: the next fix to make, then every other fix by worth, what slipped back, and what a read has checked fixed. A key may make this call on the sites it has claimed.

Who may call it: Your claimed sites.

## When to use it

- You sit down to work and want to know what is next.
- You want to see what a recent read confirmed.

## What you ask

You might say: “What should I work on next across my sites?”

```
mttr_todo({})
```

## What comes back

- The next fix, with the words to work from.
- Every other fix, by worth.
- What slipped back, what a read checked fixed, and sites changed since their last read.

A sample, with made-up sites and figures:

1. Show sources on guides (Trust), 12 pages, worth 4.1 points
2. Answer the first question right under it (Understand), 9 pages, worth 3.2 points
3. Add a tap-to-call link (Act), 22 pages, worth 2.6 points
4. Describe images (Understand), 31 pages, worth 1.4 points

## Over HTTP

```
curl "https://mttr.si/api/v1/account/work" \
  -H "Authorization: Bearer $MTTR_KEY"
```

## When it fails

| When | Status | What to do |
| --- | --- | --- |
| Your assistant has no key yet | 401 over MCP | Sign up with `mttr_signup`, then connect again with the key it gives. |

## Sources

- [Model Context Protocol: tools](https://modelcontextprotocol.io/specification/2025-06-18/server/tools), Model Context Protocol: How an assistant calls a tool.

The call in full: [mttr_todo in the API reference](https://mttr.si/docs/reference#mttr_todo).

## Goes with

- [Tasks queued for you](https://mttr.si/docs/tools/queue.md)
- [A link to your progress page](https://mttr.si/docs/tools/progress-link.md)