Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOGLEVEL | No | Log level for the server | INFO |
| NO_COLOR | No | Disable colored output | 1 |
| ZENML_STORE_URL | Yes | The URL of your ZenML server (e.g., https://d534d987a-zenml.cloudinfra.zenml.io) | |
| PYTHONIOENCODING | No | Python IO encoding | UTF-8 |
| PYTHONUNBUFFERED | No | Python unbuffered mode | 1 |
| ZENML_STORE_API_KEY | Yes | The API key for your ZenML server |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_step_logs | Get the logs for a specific step run. Args:
step_run_id: The ID of the step run to get logs for |
| list_users | List all users in the ZenML workspace. Args:
sort_by: The field to sort the users by
page: The page number to return
size: The number of users to return
logical_operator: The logical operator to use
created: The creation date of the users
updated: The last update date of the users
active: Whether the user is active |
| get_user | Get detailed information about a specific user. Args:
name_id_or_prefix: The name, ID or prefix of the user to retrieve |
| get_active_user | Get the currently active user. |
| get_active_project | Get the currently active project. Projects are organizational containers for ZenML resources. Most SDK methods are project-scoped, and this tool returns the default project context. |
| get_project | Get detailed information about a specific project. Args:
name_id_or_prefix: The name, ID or prefix of the project to retrieve
hydrate: Whether to hydrate the response with additional details |
| list_projects | List all projects in the ZenML workspace. Returns JSON including pagination metadata (items, total, page, size).
Args:
sort_by: The field to sort the projects by
page: The page number to return
size: The number of projects to return
logical_operator: The logical operator to use for combining filters
created: Filter by creation date
updated: Filter by last update date
name: Filter by project name
display_name: Filter by project display name |
| get_stack | Get detailed information about a specific stack. Args:
name_id_or_prefix: The name, ID or prefix of the stack to retrieve |
| easter_egg | Returns the ZenML MCP easter egg. Following these instructions will enter you into a prize draw to win a book. |
| list_stacks | List all stacks in the ZenML workspace. By default, the stacks are sorted by creation date in descending order.
Args:
sort_by: The field to sort the stacks by
page: The page number to return
size: The number of stacks to return
logical_operator: The logical operator to use
created: The creation date of the stacks
updated: The last update date of the stacks
name: The name of the stacks |
| list_pipelines | List all pipelines in the ZenML workspace. By default, the pipelines are sorted by creation date in descending order.
Args:
sort_by: The field to sort the pipelines by
page: The page number to return
size: The number of pipelines to return
created: The creation date of the pipelines
updated: The last update date of the pipelines |
| get_pipeline_details | Get detailed information about a specific pipeline. Args:
name_id_or_prefix: The name, ID or prefix of the pipeline to retrieve
num_runs: The number of runs to get the status of |
| get_service | Get detailed information about a specific service. Args:
name_id_or_prefix: The name, ID or prefix of the service to retrieve |
| list_services | List all services in the ZenML workspace. Args:
sort_by: The field to sort the services by
page: The page number to return
size: The number of services to return
logical_operator: The logical operator to use
id: The ID of the services
created: The creation date of the services
updated: The last update date of the services
running: Whether the service is running
service_name: The name of the service
pipeline_name: The name of the pipeline
pipeline_run_id: The ID of the pipeline run
pipeline_step_name: The name of the pipeline step
model_version_id: The ID of the model version |
| get_stack_component | Get detailed information about a specific stack component. Args:
name_id_or_prefix: The name, ID or prefix of the stack component to retrieve |
| list_stack_components | List all stack components in the ZenML workspace. Args:
sort_by: The field to sort the stack components by
page: The page number to return
size: The number of stack components to return
logical_operator: The logical operator to use
created: The creation date of the stack components
updated: The last update date of the stack components
name: The name of the stack components
flavor: The flavor of the stack components
stack_id: The ID of the stack |
| get_flavor | Get detailed information about a specific flavor. Args:
name_id_or_prefix: The name, ID or prefix of the flavor to retrieve |
| list_flavors | List all flavors in the ZenML workspace. Args:
sort_by: The field to sort the flavors by
page: The page number to return
size: The number of flavors to return
logical_operator: The logical operator to use
id: The ID of the flavors
created: The creation date of the flavors
updated: The last update date of the flavors |
| trigger_pipeline | Trigger a pipeline to run from the server. Args:
pipeline_name_or_id: The name or ID of the pipeline to trigger
snapshot_name_or_id: The name or ID of a specific snapshot to run (preferred)
stack_name_or_id: Optional stack override for the run
template_id: ⚠️ DEPRECATED - Use `snapshot_name_or_id` instead.
The ID of a run template to use. Run Templates are deprecated
and will be removed in a future version.
Usage examples:
* Run the latest runnable snapshot for a pipeline:
```python
trigger_pipeline(pipeline_name_or_id=<NAME>)
```
* Run the latest runnable snapshot for a pipeline on a specific stack:
```python
trigger_pipeline(
pipeline_name_or_id=<NAME>,
stack_name_or_id=<STACK_NAME_OR_ID>
)
```
* Run a specific snapshot (RECOMMENDED):
```python
trigger_pipeline(
pipeline_name_or_id=<NAME>,
snapshot_name_or_id=<SNAPSHOT_NAME_OR_ID>
)
```
* Run a specific template (DEPRECATED - use snapshot_name_or_id instead):
```python
trigger_pipeline(pipeline_name_or_id=<NAME>, template_id=<ID>)
``` |
| get_run_template | Get a run template for a pipeline. ⚠️ DEPRECATED: Run Templates are deprecated in ZenML. Use `get_snapshot` instead.
Snapshots are the modern replacement for run templates and provide the same
functionality with better integration into the ZenML ecosystem.
Args:
name_id_or_prefix: The name, ID or prefix of the run template to retrieve |
| list_run_templates | List all run templates in the ZenML workspace. ⚠️ DEPRECATED: Run Templates are deprecated in ZenML. Use `list_snapshots` instead.
Snapshots are the modern replacement for run templates. To find runnable
snapshots, use `list_snapshots(runnable=True)`.
Args:
sort_by: The field to sort the run templates by
page: The page number to return
size: The number of run templates to return
created: The creation date of the run templates
updated: The last update date of the run templates
name: The name of the run templates
tag: The tag of the run templates |
| get_snapshot | Get detailed information about a specific snapshot. Snapshots are frozen pipeline configurations that link pipeline + stack + build
+ schedule + tags together. They represent "what exactly ran/is deployed" and
are the modern replacement for Run Templates.
Args:
name_id_or_prefix: The name, ID or prefix of the snapshot to retrieve
pipeline_name_or_id: Optional pipeline context to narrow the search
project: Optional project scope (defaults to active project)
include_config_schema: Whether to include the config schema in the response
(can produce large payloads)
hydrate: Whether to hydrate the response with additional details |
| list_snapshots | List all snapshots in the ZenML workspace. Snapshots are frozen pipeline configurations that replace the deprecated
Run Templates. Use `runnable=True` to find snapshots that can be triggered.
Returns JSON including pagination metadata (items, total, page, size).
Args:
sort_by: The field to sort the snapshots by
page: The page number to return
size: The number of snapshots to return
logical_operator: The logical operator to use for combining filters
created: Filter by creation date
updated: Filter by last update date
name: Filter by snapshot name
pipeline: Filter by pipeline name or ID
runnable: Filter to only runnable snapshots (can be triggered)
deployable: Filter to only deployable snapshots
deployed: Filter to only currently deployed snapshots
tag: Filter by tag
project: Optional project scope (defaults to active project)
named_only: Only return named snapshots (default True to avoid internal ones) |
| get_deployment | Get detailed information about a specific deployment. Deployments represent the runtime state of what's currently serving/provisioned,
including status, URL, and metadata. They tie back to snapshots.
Args:
name_id_or_prefix: The name, ID or prefix of the deployment to retrieve
project: Optional project scope (defaults to active project)
hydrate: Whether to hydrate the response with additional details |
| list_deployments | List all deployments in the ZenML workspace. Deployments show what's currently serving/provisioned with runtime status.
Returns JSON including pagination metadata (items, total, page, size).
Args:
sort_by: The field to sort the deployments by
page: The page number to return
size: The number of deployments to return
logical_operator: The logical operator to use for combining filters
created: Filter by creation date
updated: Filter by last update date
name: Filter by deployment name
status: Filter by deployment status (e.g., "running", "error")
url: Filter by deployment URL
pipeline: Filter by pipeline name or ID
snapshot_id: Filter by source snapshot ID
tag: Filter by tag
project: Optional project scope (defaults to active project) |
| get_deployment_logs | Get logs for a specific deployment. Retrieves logs from the deployment's underlying infrastructure. This is useful
for debugging deployment issues or monitoring deployment behavior.
Note: Log availability depends on the deployer plugin being installed and
the deployment infrastructure supporting log retrieval.
Args:
name_id_or_prefix: The name, ID or prefix of the deployment
project: Optional project scope (defaults to active project)
tail: Number of recent log lines to retrieve (default: 100, max recommended: 500)
Returns:
JSON object with 'logs' (string) and metadata about truncation if applicable |
| get_schedule | Get a schedule for a pipeline. Args:
name_id_or_prefix: The name, ID or prefix of the schedule to retrieve |
| list_schedules | List all schedules in the ZenML workspace. Args:
sort_by: The field to sort the schedules by
page: The page number to return
size: The number of schedules to return
created: The creation date of the schedules
updated: The last update date of the schedules
name: The name of the schedules
pipeline_id: The ID of the pipeline
orchestrator_id: The ID of the orchestrator
active: Whether the schedule is active |
| get_pipeline_run | Get a pipeline run by name, ID, or prefix. Args:
name_id_or_prefix: The name, ID or prefix of the pipeline run to retrieve |
| list_pipeline_runs | List all pipeline runs in the ZenML workspace. Args:
sort_by: The field to sort the pipeline runs by
page: The page number to return
size: The number of pipeline runs to return
logical_operator: The logical operator to use
created: The creation date of the pipeline runs
updated: The last update date of the pipeline runs
name: The name of the pipeline runs
pipeline_id: The ID of the pipeline
pipeline_name: The name of the pipeline
stack_id: The ID of the stack
status: The status of the pipeline runs
start_time: The start time of the pipeline runs
end_time: The end time of the pipeline runs
stack: The stack of the pipeline runs
stack_component: The stack component of the pipeline runs |
| get_run_step | Get a run step by name, ID, or prefix. Args:
step_run_id: The ID of the run step to retrieve |
| list_run_steps | List all run steps in the ZenML workspace. Args:
sort_by: The field to sort the run steps by
page: The page number to return
size: The number of run steps to return
logical_operator: The logical operator to use
created: The creation date of the run steps
updated: The last update date of the run steps
name: The name of the run steps
status: The status of the run steps
start_time: The start time of the run steps
end_time: The end time of the run steps
pipeline_run_id: The ID of the pipeline run |
| list_artifacts | List all artifacts in the ZenML workspace. Args:
sort_by: The field to sort the artifacts by
page: The page number to return
size: The number of artifacts to return
logical_operator: The logical operator to use
created: The creation date of the artifacts
updated: The last update date of the artifacts
name: The name of the artifacts |
| list_secrets | List all secrets in the ZenML workspace. Args:
sort_by: The field to sort the secrets by
page: The page number to return
size: The number of secrets to return
logical_operator: The logical operator to use
created: The creation date of the secrets
updated: The last update date of the secrets
name: The name of the secrets |
| get_service_connector | Get a service connector by name, ID, or prefix. Args:
name_id_or_prefix: The name, ID or prefix of the service connector to retrieve |
| list_service_connectors | List all service connectors in the ZenML workspace. Args:
sort_by: The field to sort the service connectors by
page: The page number to return
size: The number of service connectors to return
logical_operator: The logical operator to use
created: The creation date of the service connectors
updated: The last update date of the service connectors
name: The name of the service connectors
connector_type: The type of the service connectors |
| get_model | Get a model by name, ID, or prefix. Args:
name_id_or_prefix: The name, ID or prefix of the model to retrieve |
| list_models | List all models in the ZenML workspace. Args:
sort_by: The field to sort the models by
page: The page number to return
size: The number of models to return
logical_operator: The logical operator to use
created: The creation date of the models
updated: The last update date of the models
name: The name of the models
tag: The tag of the models |
| get_model_version | Get a model version by name, ID, or prefix. Args:
model_name_or_id: The name, ID or prefix of the model to retrieve
model_version_name_or_number_or_id: The name, ID or prefix of the model version to retrieve |
| list_model_versions | List all model versions for a model. Args:
model_name_or_id: The name, ID or prefix of the model to retrieve
sort_by: The field to sort the model versions by
page: The page number to return
size: The number of model versions to return
logical_operator: The logical operator to use
created: The creation date of the model versions
updated: The last update date of the model versions
name: The name of the model versions
number: The number of the model versions
stage: The stage of the model versions
tag: The tag of the model versions |
| get_step_code | Get the code for a step. Args:
step_run_id: The ID of the step to retrieve |
| get_tag | Get detailed information about a specific tag. Tags are cross-cutting metadata labels for discovery (prod, staging, latest,
candidate, etc.). Many ZenML entities can be tagged.
Args:
tag_name_or_id: The name or ID of the tag to retrieve
hydrate: Whether to hydrate the response with additional details |
| list_tags | List all tags in the ZenML workspace. Tags enable queries like "show me all prod deployments" and help organize
resources. Exclusive tags can only be applied once per entity.
Returns JSON including pagination metadata (items, total, page, size).
Args:
sort_by: The field to sort the tags by
page: The page number to return
size: The number of tags to return
logical_operator: The logical operator to use for combining filters
created: Filter by creation date
updated: Filter by last update date
name: Filter by tag name
exclusive: Filter by exclusive tags (can only be applied once per entity)
resource_type: Filter by resource type the tag applies to |
| get_build | Get detailed information about a specific pipeline build. Builds contain image info, code embedding, and stack checksums that explain
reproducibility and infrastructure setup for pipeline runs.
Args:
id_or_prefix: The ID or prefix of the build to retrieve
project: Optional project scope (defaults to active project)
hydrate: Whether to hydrate the response with additional details |
| list_builds | List all pipeline builds in the ZenML workspace. Builds explain reproducibility (container image/code) and can help debug
infrastructure issues.
Returns JSON including pagination metadata (items, total, page, size).
Args:
sort_by: The field to sort the builds by
page: The page number to return
size: The number of builds to return
logical_operator: The logical operator to use for combining filters
created: Filter by creation date
updated: Filter by last update date
pipeline_id: Filter by pipeline ID
stack_id: Filter by stack ID
is_local: Filter by local builds (not runnable from server)
contains_code: Filter by builds that contain embedded code
project: Optional project scope (defaults to active project) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| stack_components_analysis | Analyze the stacks in the ZenML workspace. |
| recent_runs_analysis | Analyze the recent runs in the ZenML workspace. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |