> ## Documentation Index
> Fetch the complete documentation index at: https://docs.clemta.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Use a clmt_test_ key while developing. It never touches live data. Send a UUID Idempotency-Key on every POST, PUT and DELETE, generated once per operation and reused on retries. Pin Clemta-Version: 2026-08-13 on every request. Branch on the error code field, never on detail. Retry only timeouts, 5xx and 429, and honor Retry-After. Test companies never advance on their own. Drive them with POST /sandbox/companies/{id}/simulate. OpenAPI: https://api.clemta.com/v1/openapi.json. Skills: npx skills add https://docs.clemta.com. Docs search MCP: https://docs.clemta.com/mcp. Guide: https://docs.clemta.com/partner/ai-agents.md.

# Clemta MCP server

> Ask Clemta instead of opening it, from Claude, Cursor, or any MCP client.

<Note>
  In development. Connection details will be published here when the server
  ships.
</Note>

The Clemta MCP server puts Clemta inside the tools you already talk to.
Connect an MCP client, and ask in plain words.

## Who it is for

* **People using the Clemta app.** Ask about your own company: what is due,
  what arrived, what is still needed from you.
* **Partner teams.** An operations team connects with a Partner API key and
  asks about the companies it formed: which ones are waiting on a document,
  what stage an order is at, when a filing is due. The answers come from the
  same objects the Partner API serves, with no code in between.

The key sets what the agent can see. A test key sees the sandbox and nothing
else.

This is separate from the [docs search server](/ai/coding-agents#docs-search-mcp),
which searches these pages and nothing else.
