Skip to main content
CoreWeave Mission Control MCP is a hosted Model Context Protocol (MCP) server for CoreWeave infrastructure. It connects MCP-compatible clients, such as Claude Code, Cursor, and the ChatGPT desktop app, to tools for observing, triaging, optimizing, and performing supported changes in CoreWeave environments. With a CoreWeave API token, you can ask natural-language questions about your infrastructure and let an agent gather current evidence from metrics, logs, dashboards, documentation, cluster state, Node details, and object storage context. The agent works inside the same visibility boundary as your token, so it can access only resources available to your token. CoreWeave hosts the server, so you don’t need to deploy or operate it. Point your client at the endpoint and authenticate with a token. Most tools are read-only. CoreWeave can enable limited write tools for an organization, and those tools can change supported resources.

​
Mission Control MCP capabilities

Mission Control MCP combines tool families in one connection so an agent can perform a multi-step investigation. It coordinates access to dashboards, command-line interfaces (CLIs), and documentation. It doesn’t replace them. Mission Control MCP provides the following capabilities:
  • Observability: query metrics, search logs, inspect dashboards and the queries behind their panels, and discover datasources, backed by Grafana-compatible systems.
  • CoreWeave documentation: search and read CoreWeave public documentation so an agent answers product and API questions from documentation rather than model memory.
  • CoreWeave resources: inspect clusters, Nodes, CoreWeave SUNK resources, and CoreWeave AI Object Storage buckets, then connect that state to observability data.
  • Write actions: apply a Kubernetes manifest to a CoreWeave Kubernetes Service (CKS) cluster and update supported CoreWeave Inference deployment fields, where enabled for your organization.
For documented tool inputs and outputs, see the Mission Control MCP tool reference.

​
How teams use Mission Control MCP

Mission Control MCP supports the following roles:
  • AI researchers and ML engineers can stay in their editor while they ask for GPU health signals, Node status, workload logs, or relevant dashboards, then follow up with further questions.
  • Platform and infrastructure teams can assemble an evidence chain that shows what is affected, which metrics changed, which errors appear in the logs, and which dashboards are relevant.
  • Application teams and operators can answer operational questions that cross product surfaces, such as combining workload logs, metrics, and object storage state to investigate performance issues in training jobs.
  • Domain experts can frame an investigation while the agent coordinates tool calls and turns operational telemetry into tables, prototypes, and next steps.

​
Set up Mission Control MCP

To connect a client and start calling the tools, see Configure Mission Control MCP. Setup requires a CoreWeave API token and an MCP-compatible client, such as Claude Code, Cursor, or the ChatGPT desktop app. Use the following resources to learn more about Mission Control:

Mission Control Agent

Use CoreWeave’s conversational interface in the Cloud Console.

Configure Mission Control MCP

Connect Claude Code, Cursor, the ChatGPT desktop app, or another MCP client to the hosted server.

Tool reference

Mission Control MCP tools, grouped by family, with inputs and outputs.

CoreWeave Grafana

Managed Grafana dashboards, metrics, and logs that Mission Control MCP tools observe.

CoreWeave AI Object Storage

S3-compatible object storage that the object storage tools inspect.
Last modified on September 29, 2026