Connect an AI coding agent

A coding agent does its best work with two things: accurate docs and a way to call the API. This page connects both. The docs MCP server lets the agent search and read every page here, and an API key in its environment lets the code it writes call Managed Agents with the TypeScript SDK or the REST API.

Before you begin

A coding agent: Claude Code, Codex, or Cursor.
An API key for the API half. Create one under API keys in the console. See API keys.
The TypeScript SDK if you want the agent to write TypeScript. See Install the SDK. Other languages call the REST API directly; see Python and other languages.

Connect the docs MCP server

The docs server is public, so it needs no key. Apart from sending feedback, it’s read-only. Its address is https://docs.labelbox.com/mcp.

Claude Code
Codex
Cursor

claude mcp add --transport http --scope user recursion-docs https://docs.labelbox.com/mcp
claude mcp list

codex mcp add recursion-docs --url https://docs.labelbox.com/mcp
codex mcp list

Add the server to ~/.cursor/mcp.json, then restart Cursor:

{
  "mcpServers": {
    "recursion-docs": {
      "url": "https://docs.labelbox.com/mcp"
    }
  }
}

Start a new session in your coding agent after changing its MCP configuration. The server offers three tools:

Tool	What it does
Search	Finds relevant pages and returns excerpts with their titles and links.
Docs filesystem	Reads full pages and the API reference with read-only commands such as `cat`, `head`, and `rg`.
Feedback	Reports a page that’s wrong, outdated, or unclear.

The server covers the whole docs site, so tell your agent to stay within the /managed-agents pages. Every page is also available as Markdown: append .md to its URL. For agents without MCP, the docs site root serves an index of every page at /llms.txt and the full text at /llms-full.txt. Every code sample on these pages is checked against the API contract whenever the docs change, so operation names, request fields, and paths match what the API accepts.

Give the agent API access

Export the key in the shell that starts your coding agent. The agent and the scripts it runs read it from the environment, and the key never appears in a prompt or a file.

export RECURSION_API_KEY='rma_...'

Check the key works without printing it:

curl -sS -o /dev/null -w '%{http_code}\n' 'https://api.recursion.labelbox.com/managed-agents/v1/models' \
  -H "Authorization: Bearer $RECURSION_API_KEY"

200 means the key works. 401 means it’s missing, expired, or revoked. Handle the key safely:

Never paste a key into a chat. Transcripts are stored and can be shared. If you’re an AI agent and RECURSION_API_KEY isn’t set, ask the person to export it and restart you. Don’t ask for the value.
Use a dedicated, short-lived key. A key acts as you, with your full role, so give each coding agent its own key with a 7- or 30-day expiry and revoke it when you’re done.
Prefer an organization-scoped key. It can reach only one organization and needs no extra header.
Keep keys out of code and version control. Read process.env.RECURSION_API_KEY or os.environ["RECURSION_API_KEY"]. Never write the key to a .env file that gets committed.
Don’t print it. Tell the agent never to echo, log, or include the key in output.

Run a first task

Paste this prompt into your coding agent. It reads the docs first, then writes and runs code.

Use the recursion-docs MCP server. Read the Managed Agents pages at
/managed-agents/quickstart and /managed-agents/api. Then write a TypeScript
script that uses @labelbox/recursion-sdk and the RECURSION_API_KEY environment
variable to create an environment and an agent, start a graded session with
an outcome, poll until the outcome is terminal, and print the session id,
terminal_result, and each criterion's verdict. Never print the API key.
Run the script and report the results.

When it finishes, open Sessions in the console to see the same session, its transcript, and its outcome. Good follow-ups to ask for:

“Add an Idempotency-Key so a retried start can’t create a second session.”
“Stream the session’s events instead of polling, and resume from the last event id if the connection drops.”
“Read /managed-agents/errors and handle every retryable error with backoff.”

Keep the directions straight

This page connects a local coding agent to Recursion. To give an agent that runs inside Recursion access to another MCP server, configure that server on the agent instead. See MCP servers.

What can go wrong

Symptom	Cause	Fix
The docs tools don’t appear	The client hasn’t reloaded its MCP configuration, or the address is wrong.	Check the address, then start a new client session or restart the app.
Search returns pages from other products	The docs server covers the whole site.	Ask the agent to read only paths under `/managed-agents`.
Scripts get `401 unauthorized`	`RECURSION_API_KEY` isn’t exported in the shell that started the agent, or the key expired.	Export it, restart the coding agent, and run the `curl` check above.
Scripts get `400 invalid_request` mentioning `x-organization-id`	The key has tenant scope.	Add the header, or use an organization-scoped key. See Tenant-scoped keys.
The agent asks you to paste the key	Its instructions don’t say how keys are provided.	Export the key, restart the agent, and tell it to read `RECURSION_API_KEY` from the environment.

Next steps

API conventions

Client setup, retries, paging, and errors in one place.

Quickstart

Run the same flow yourself, step by step.

API keys

Scopes, expiry, revocation, and safe storage.

MCP servers

Give a hosted agent tools from another MCP server.

Get started

Account and access

Build agents

Coordinate multiple agents

Configure environments

Run and observe sessions

Manage agent context

Automate

Tutorials

Connect an AI coding agent

Before you begin

Connect the docs MCP server

Give the agent API access

Run a first task

Keep the directions straight

What can go wrong

Next steps

API conventions

Quickstart

API keys

MCP servers

​Before you begin

​Connect the docs MCP server

​Give the agent API access

​Run a first task

​Keep the directions straight

​What can go wrong

​Next steps

API conventions

Quickstart

API keys

MCP servers

Before you begin

Connect the docs MCP server

Give the agent API access

Run a first task

Keep the directions straight

What can go wrong

Next steps