MCP server to connect an MCP client (Cursor, Claude Desktop etc) with your ZenML MLOps and LLMOps pipelines
Drift inferred · capture-to-capture
No drift recorded — single capability capture; advisories appear once its surface changes.
tools
-
diagnose_zenml_setup
Diagnose server setup (env vars, SDK, connectivity, auth). Works even when misconfigured.
-
get_active_project
Get the currently active project
-
get_build
Get build details (image, code embedding)
-
get_deployment
Get a deployment's runtime status and URL
-
get_deployment_logs
Get bounded logs from a deployment (tail=100 default, max 1000)
-
get_project
Get project details by name/ID
-
get_run_template
Use get_snapshot instead
-
get_snapshot
Get a frozen pipeline configuration by name/ID
-
get_tag
Get tag details (exclusive, colors)
-
list_artifacts
Artifact metadata
-
list_builds
List builds with filters (is_local, contains_code)
-
list_deployments
List deployments with filters (status, pipeline, tag)
-
list_projects
List all projects
-
list_run_templates
Use list_snapshots instead
-
list_secrets
Secret names (not values)
-
list_snapshots
List snapshots with filters (runnable, deployable, deployed, tag)
-
list_tags
List tags with filters (resource_type)
-
most_recent_runs
Get N most recent runs
-
open_pipeline_run_dashboard
Open interactive pipeline runs dashboard (MCP App)
-
open_run_activity_chart
Open 30-day run activity bar chart (MCP App)
-
recent_runs_analysis
Analyze recent pipeline runs
-
stack_components_analysis
Analyze stack component usage
-
trigger_pipeline
Trigger a pipeline run (prefer snapshot_name_or_id parameter)
last analysis: too-large
No code evidence — the analyzed source reached for no tracked permissions, tools, or hooks.