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

# Tools and scopes

> How Rally's MCP tools are named, how to connect a smaller set, and the helper tools every connection gets.

## How tools are named

Every tool is a verb and a noun: `list_programs`, `create_brief`, `publish_brief`, `approve_payout`, `generate_ai_ad`. Reads are free to call; writes change your workspace and are audited.

Creating and publishing are separate steps, as in the app. A brief exists as a draft after `create_brief` and reaches creators after `publish_brief`. An agent that reads the tool descriptions follows this on its own.

## Connect a smaller set of tools

The full catalog is more than 400 tools. Claude Code and Codex handle that; Cursor and some other clients warn or drop tools past a few dozen. Add a scope to the URL to connect a subset:

| URL | What you get |
| - | - |
| `/mcp` | Everything the key's role allows. |
| `/mcp?profile=core` | About 45 tools to run a program day to day: programs, briefs, creators, content, AI ads, knowledge, tracking, payouts. |
| `/mcp?profile=onboarding` | Set a workspace up end to end: brand, knowledge, program, rubric, briefs, tracking, domains, embeds. |
| `/mcp?domains=programs,briefs,ads` | Whole areas. Domains: `programs`, `briefs`, `creators`, `content`, `ai`, `ads`, `knowledge`, `finance`, `insights`, `settings`. |
| `/mcp?tools=list_programs,create_brief` | Exactly the tools you name. |

Scopes combine: `/mcp?profile=core&domains=ads` is the core profile plus every ads tool. The `rally_*` helper tools below always come along.

<Note>
  A scope only narrows what the client sees. The key's role still decides what the agent may do; a scope never grants more than the role allows.
</Note>

## Helper tools

Five tools exist only for agents and are present on every connection.

| Tool | What it does |
| - | - |
| `rally_whoami` | The workspace, the key's role, whether it is autonomous, your plan and what is left of this month's limits. |
| `rally_setup_status` | The setup checklist: which steps are done, what finishes each, and which parts only a person can do. |
| `rally_upload_asset` | Upload a file from a URL or as base64 and get an asset id for logos, brief files, reference clips and music. Up to 50 MB. |
| `rally_wait_for` | Wait for a long job (an AI ad, an AI creator build, a sourcing run, an ad launch, a pending approval) instead of polling. Waits up to 300 seconds per call. |
| `rally_confirmations` | The actions an agent asked for that need a person: pending, approved, cancelled, with results. |

## Resources and prompts

Alongside tools, the server offers:

* **Resources**: Rally's own documentation (`rally://docs/...`), the setup runbook and the program templates, so the agent can read how things work rather than guess.
* **Prompts**: `onboard_brand` (set a workspace up from your website), `weekly_review` (health, exceptions, learnings and what to do about them), `launch_campaign` (a brief to published ads). Clients that support prompts list them as slash commands or templates.

The runbook is also a plain file at `https://app.runrally.io/mcp/skill.md`.

## Limits

* 600 calls a minute per key, of which 60 may be writes. Past that the agent gets a `rate_limited` error and should slow down.
* Plan limits apply exactly as in the app. When one is reached the agent gets an error with an upgrade hint.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.