> ## 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.

# Agent MCP

> Talk to a deployed Corvic agent from any MCP-compatible client.

**Agent MCP** lets you connect to a single deployed agent from your own tools — ask it questions, retrieve the cited resources behind its answers, and trigger sync/deploy. It works with any MCP-compatible client: Claude, Cursor, agent frameworks, or a custom client of your own.

For access to a whole room — pipelines, memories, lenses, and data — use [Room MCP](/integrations/room-mcp) instead.

## Get connected

Open your agent's **Integration & Sharing → Integration** tab and copy its **MCP URL** and **Access Token**. See [Agents](/features/agents#mcp-integration).

Configure your MCP client with that URL and send the token as a Bearer header:

|             | Value                                  |
| ----------- | -------------------------------------- |
| **MCP URL** | From the agent's Integration tab       |
| **Auth**    | `Authorization: Bearer <ACCESS_TOKEN>` |

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

<Tip>
  The room's **MCP Playground** is the fastest way to explore before wiring a client up: it lists every tool with its input schema and lets you call them live, showing the exact requests and raw responses an MCP client would see.
</Tip>

## Available tools

| Tool                        | Description                                                                                              |
| --------------------------- | -------------------------------------------------------------------------------------------------------- |
| `query`                     | Ask the agent a question and get its grounded answer, optionally with citations (`with_citation: true`). |
| `get_resource_download_url` | Get download URLs for resource IDs — typically the citations returned by `query`.                        |
| `get_resources`             | Look up resources by their original file paths.                                                          |
| `sync_agent_data_app`       | Sync the agent's workflow to pick up the latest data.                                                    |
| `deploy_agent`              | Deploy the agent to apply the latest changes.                                                            |

Your client's tool listing always reflects the live set — descriptions and input schemas come straight from the agent.

## A typical exchange

<Steps>
  <Step title="Ask">
    Call `query` with your question and `with_citation: true`. The agent answers from its configured knowledge, citing the rows and documents it used.
  </Step>

  <Step title="Follow the citations">
    Pass the cited resource IDs to `get_resource_download_url` to fetch the underlying documents.
  </Step>

  <Step title="Keep it fresh">
    After new data lands, call `sync_agent_data_app` and then `deploy_agent` so the agent answers from the latest state.
  </Step>
</Steps>

## Related

<CardGroup cols={2}>
  <Card title="MCP API Overview" icon="diagram-project" href="/integrations/mcp-overview">
    Agent vs. room access and credentials.
  </Card>

  <Card title="Room MCP" icon="folder" href="/integrations/room-mcp">
    The full room surface: pipelines, memories, lenses, agents, and data access.
  </Card>

  <Card title="Agents" icon="robot" href="/features/agents">
    Configure and deploy the agent behind this endpoint.
  </Card>

  <Card title="Sharing" icon="share-nodes" href="/features/sharing">
    Share chats and artifacts without an integration.
  </Card>
</CardGroup>