Skip to main content
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.
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. 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).

​
What it can do

Deployments

List, deploy (base or fine-tuned), start/stop/restart/resume/pause, recover, health-check, and schedule model deployments.

Fine-tuning

Create, list, monitor, retry, cancel, and recover jobs; list tuned models; fetch and download outputs.

Datasets

List and inspect datasets, get an upload URL, download, and delete.

GPU availability

Check GPU availability before you deploy.

Logs

Read and collect job, deployment, and serving engine logs.

Inference pools

Put several deployments behind one endpoint, let a managed pool keep its size, and run worker tasks on a pool.
The full, explained list is in MCP tools.

​
What it can’t do (and other limits)

Read these before you connect a key.
  • It is not the inference endpoint. The MCP server operates infrastructure; it doesn’t replace the OpenAI/Anthropic-compatible API 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 undo for a terminate. Only deploy_base_model has a dry_run option.
  • 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.
  • Managed pools spend from your wallet. A pool with a member template and a desired size deploys, replaces, and removes its own members, each billed like any deployment, where managed pools are switched on. A pool without a template never creates or changes deployments.
  • It doesn’t manage account administration. Users, roles, billing top-ups, and dashboard account settings are handled in the dashboard, not through these tools.

​
Next step

Set up the MCP server

Register Valkyrie in your client, with the transport and auth details that matter.