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

# MCP overview

> Connect AI assistants to your rocketblue organization via the Model Context Protocol.

## What is rocketblue MCP?

rocketblue exposes an [MCP](https://modelcontextprotocol.io) (Model Context Protocol) server so AI assistants — such as Cursor, Claude Desktop, or other MCP-compatible clients — can read and manage your organization's rocketblue data using natural language.

MCP wraps the same **organization API** you use for HTTP integrations. Your API key, rate limits, and permissions are identical whether you call REST endpoints directly or invoke MCP tools.

<CardGroup cols={2}>
  <Card title="Connect a client" icon="link" href="/rocketblue-mcp/connect">
    Set up Cursor, Claude Desktop, or another MCP client.
  </Card>

  <Card title="Use cases" icon="sparkles" href="/rocketblue-mcp/use-cases">
    Practical AI visibility automation workflows.
  </Card>

  <Card title="Tools reference" icon="wrench" href="/rocketblue-mcp/tools">
    Full list of MCP tools and what each one does.
  </Card>

  <Card title="Best practices" icon="lightbulb" href="/rocketblue-mcp/best-practices">
    How agents should work with prompts, quotas, and scheduling.
  </Card>
</CardGroup>

## Prerequisites

1. **API access enabled** — MCP is available when API access is enabled for your organization. In the rocketblue app, go to **Settings → API** and turn on the API.
2. **API key** — Copy your key from **Settings → API**. MCP uses the same key as REST calls.
3. **MCP endpoint** — Find your MCP URL under **Settings → MCP**. The default is:

```text theme={null}
https://app.rocketblue.ai/api/mcp
```

<Note>
  MCP is currently in closed beta. If you do not see the API or MCP tabs in Settings, contact your rocketblue account team to request access.
</Note>

## What you can do with MCP

| Area                   | Examples                                                                            |
| ---------------------- | ----------------------------------------------------------------------------------- |
| **Discovery**          | List brands, fetch organization and brand context, read the built-in usage guide    |
| **Analysis data**      | Pull run history, per-prompt results, run stats, sources, and content suggestions   |
| **Web search queries** | Inspect the queries LLMs ran while answering your prompts                           |
| **Created content**    | List and export markdown drafts created in the app                                  |
| **Perception**         | Read perception prompts and responses; add new perception prompts                   |
| **Prompt management**  | Create topics and prompts, batch-import prompt sets, delete prompts or whole topics |

See [MCP use cases](/rocketblue-mcp/use-cases) for end-to-end automation recipes (weekly digests, competitor watches, content pipelines, and more).

## How MCP relates to the REST API

Each MCP tool maps to one or more REST endpoints under `https://app.rocketblue.ai/api`. For example, `list_brands` calls `GET /v1/brands`, and `get_run_stats` calls `GET /v1/runs/{runId}/stats`.

Agents should call **`get_organization_context`** once per session and **`get_brand_context`** before working with a specific brand. See [Best practices](/rocketblue-mcp/best-practices) for the recommended workflow.

## Transport and protocol

* **Transport:** HTTP (streamable HTTP MCP)
* **Authentication:** `x-spotlight-api-key` header (same as the REST API)
* **Scope:** One API key = one organization; all tools are scoped to that organization

## Next steps

1. [Connect your MCP client](/rocketblue-mcp/connect)
2. [Browse use cases](/rocketblue-mcp/use-cases)
3. [Review available tools](/rocketblue-mcp/tools)
4. [Follow agent best practices](/rocketblue-mcp/best-practices)