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

# MCP server overview

> Operate Valkyrie from an AI agent through the Model Context Protocol, what it is, and what it can and can't do.

Valkyrie ships a built-in **Model Context Protocol (MCP) server**. Connect it to an
MCP-capable client, Claude Code, Claude Desktop, Cursor, and others, and the
assistant gets tools to **operate your Valkyrie account**: deploy and manage models,
run and monitor fine-tuning jobs, inspect GPUs and cloud state, read logs, and work
with datasets.

<Info>
  This is the **control plane**, it's how an agent *operates* Valkyrie. It is **not**
  how you chat with a model. To use a Valkyrie-hosted model as your LLM, use the
  inference API instead, see [Connect a model](/connect/overview). The two are
  separate and can be used together (e.g. a Valkyrie model as your agent's brain, plus
  these tools to manage infrastructure).
</Info>

## What it can do

<CardGroup cols={2}>
  <Card title="Deployments" icon="server">
    List, deploy (base or fine-tuned), start/stop/restart/resume/pause, recover,
    health-check, and schedule model deployments.
  </Card>

  <Card title="Fine-tuning" icon="graduation-cap">
    Create, list, monitor, retry, cancel, and recover jobs; list tuned models; fetch
    and download outputs.
  </Card>

  <Card title="Datasets" icon="database">
    List and inspect datasets, get an upload URL, download, and delete.
  </Card>

  <Card title="Cloud & GPUs" icon="microchip">
    Check account status/balances, GPU availability, and running instances; sync,
    adopt, or stop instances.
  </Card>

  <Card title="Logs" icon="file-lines">
    Read and collect job, deployment, and vLLM service logs.
  </Card>

  <Card title="Inference pools" icon="layer-group">
    Inspect and manage pool configuration, capacity, and member leases.
  </Card>
</CardGroup>

The full, explained list is in [MCP tools](/mcp/tools).

## What it can't do (and other limits)

<Warning>
  Read these before you connect a key.
</Warning>

* **It is not the inference endpoint.** The MCP server operates infrastructure; it
  doesn't replace the [OpenAI/Anthropic-compatible API](/connect/overview) you call to
  actually run prompts against a model.
* **There is no read-only mode.** The tool set always includes **mutating** tools,
  `deploy_base_model`, `stop_deployment`, `terminate_cluster`, `delete_dataset`, and
  more. They act on whatever environment your key points at, and some **spend from
  your wallet** or **tear down running resources**. There is no dry-run or undo for a
  terminate.
* **Keys are per-environment.** A key operates only its own environment; a key from
  one environment returns *Invalid API key* against another. Cross-environment
  ownership is guarded, you can't operate another environment's resources.
* **Logs are workload logs, not platform logs.** The log tools return your job,
  deployment, and serving-engine output, not Valkyrie's own internal application or
  crash logs.
* **Pool administration never provisions or mutates serving deployments.** Inference-pool
  tools manage pool configuration and leases only; they don't create or change the
  underlying model deployments.
* **It doesn't manage account administration.** Users, roles, billing top-ups, and
  dashboard account settings are handled in the [dashboard](/dashboard/overview), not
  through these tools.

## Next step

<Card title="Set up the MCP server" icon="plug" href="/mcp/setup">
  Register Valkyrie in your client, with the transport and auth details that matter.
</Card>