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

# Integrate Corvic via MCP

> Bring Corvic's agents and rooms into your own applications over the Model Context Protocol.

Corvic exposes its capabilities through the **Model Context Protocol (MCP)** — an open standard that lets AI systems and applications consume tools and data in a uniform way. With MCP you can call Corvic from your own code, notebooks, agent frameworks, or backend services.

## Two levels of access

| Level         | What it gives you                                                                                     | Guide                                          |
| ------------- | ----------------------------------------------------------------------------------------------------- | ---------------------------------------------- |
| **Agent MCP** | Talk to a deployed agent — ask questions, retrieve cited resources, and trigger sync/deploy           | [Agent MCP](/integrations/mcp-api-integration) |
| **Room MCP**  | Programmatic access to a room's workflows and feature views, including downloading their Parquet data | [Room MCP](/integrations/room-mcp)             |

Use **Agent MCP** when you want grounded answers from a configured agent. Use **Room MCP** when you want the underlying data and pipeline objects in a room.

## Getting your credentials

Every MCP request needs an endpoint URL and an access token (sent as a Bearer token):

* **Agent MCP** — open your agent's **Integration & Sharing → Integration** tab to copy its **MCP URL** and **Access Token**. See [Agents](/features/agents#mcp-integration).
* **Room MCP** — use the Corvic MCP endpoint with a Bearer access token and the target **Room ID**.

<Warning>
  Treat access tokens like passwords. Don't commit them to source control — load them from environment variables or a secrets manager.
</Warning>

## Connect from any platform

Agent MCP works with any MCP-compatible client, so you can call Corvic from Python, notebooks, agent frameworks like OpenAI, CrewAI, or LangChain, or your own backend services.

## Related

<CardGroup cols={2}>
  <Card title="Agent MCP" icon="robot" href="/integrations/mcp-api-integration">
    Tools for talking to a deployed agent.
  </Card>

  <Card title="Room MCP" icon="folder" href="/integrations/room-mcp">
    List workflows and download feature view data.
  </Card>

  <Card title="Connect External Services" icon="key" href="/integrations/connect-services">
    The other direction — services into Corvic.
  </Card>
</CardGroup>