Mcp Zenml
by zenml-iocommunityv1.5.1
44
13
This MCP server exposes ZenML API functionality through the Model Context Protocol, allowing clients to read ZenML entities such as projects, pipelines, runs, deployments, models, and related metadata. It also supports triggering pipeline runs from snapshots and includes diagnostics plus two experimental interactive MCP apps.
From the registry: MCP server for ZenML - browse stacks, pipelines, runs, artifacts & trigger pipeline runs via API
Install & configure
Prerequisites
- required
- requiredZenML service account tokenCreate a service account and generate an API key in the ZenML UI
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `mcp-zenml` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **ZenML server** — Deployed ZenML server >= 0.93.0 (https://cloud.zenml.io)
- **ZenML service account token** — Create a service account and generate an API key in the ZenML UI
Canonical MCP server config (stdio transport):
- command: `docker`
- args: ["run","-i","--rm","-e","ZENML_STORE_URL","-e","ZENML_STORE_API_KEY","zenmldocker/mcp-zenml:latest"]
- required environment variables:
- `ZENML_STORE_URL`: ZenML server URL (example: `https://your-zenml-server.example.com`)
- `ZENML_STORE_API_KEY`: ZenML service account API key (example: `<your-api-key>`)
- optional environment variables:
- `ZENML_ACTIVE_PROJECT_ID`: Active ZenML project ID (required for pipeline tools) (example: `<your-project-id>`)
Note: Also available via uv local install. Docker image recommended.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: Also available via uv local install. Docker image recommended.
Tools (48)
get_snapshot
Get a frozen pipeline configuration by name or ID
list_snapshots
List snapshots with filters such as runnable, deployable, deployed, and tag
get_deployment
Get a deployment's runtime status and URL
list_deployments
List deployments with filters such as status, pipeline, and tag
get_deployment_logs
Get bounded logs from a deployment
trigger_pipeline
Trigger a pipeline run using a snapshot or deprecated run template
get_active_project
Get the currently active project
get_project
Get project details by name or ID
list_projects
List all projects
get_tag
Get tag details
list_tags
List tags with filters
get_build
Get build details such as image and code embedding
list_builds
List builds with filters
get_user
Get user details
Environment variables
ZENML_STORE_URLrequiredURL of the ZenML server to connect toZENML_STORE_API_KEYrequiredAPI key/token used to authenticate with the ZenML serverZENML_ACTIVE_PROJECT_IDrequiredActive project ID required for pipeline run tools and MCP appsPackages
docker.io/zenmldocker/mcp-zenml:1.5.1
ocitransport: stdio
Details
- Language
- Python
- License
- MIT
- Released
- Mar 16, 2026
- Last commit
- Apr 7, 2026
- Registry name
- io.github.zenml-io/mcp-zenml