Enables AI agents to inspect Docker containers, images, volumes, and compose projects through Docker's official MCP server. Debug local development stacks by having the agent query container state, tail logs, and inspect networking. Supports both local Docker and Docker Desktop contexts.
Use cases
- Developer diagnoses failing container by inspecting logs and environment variables
- DevOps agent checks container health status during deployment verification
- SRE agent inspects resource usage to identify memory leak suspects
- Backend developer restarts specific services in a compose stack
- QA agent verifies containers are running expected versions after test runs
Key features
- Claude Desktop
- Cursor
- Codex
Frequently Asked Questions
- Does this work with Docker Desktop on macOS and Windows?
- Yes, the server connects to the Docker daemon via the standard socket. Docker Desktop exposes this socket by default on both macOS and Windows.
- Can agents modify containers, not just read them?
- Yes, agents can start, stop, restart, and remove containers. They can also exec into containers to run commands. Use caution as these are destructive operations.
- What about Kubernetes clusters instead of plain Docker?
- This server works with Docker, not Kubernetes directly. For Kubernetes, use the separate Kubernetes MCP server which uses the Kubernetes API.
Related
Related
3 Indexed items
Vercel MCP
Provides AI agents access to Vercel projects, deployments, logs, and documentation through Vercel's official MCP endpoint with OAuth authentication. Developers can debug deployment issues, inspect preview URLs, and manage project settings directly from the IDE.
Figma MCP
Provides AI agents access to Figma designs, components, variables, frames, and FigJam whiteboards through Figma's official MCP integration. Developers can implement designs without switching to Figma, and designers can sync annotations. Reduces miscommunication between design and code.
Cloudflare MCP
Bridges AI agents to Cloudflare Workers, KV storage, R2 object storage, and D1 databases for edge deployment inspection and management. Agents can check Workers status, inspect KV namespaces, query D1 databases, and monitor R2 buckets directly from the coding environment.