ZenML MCP Server

Official

Overview Schema Source Related Servers Discussions Admin

trigger_pipeline

Trigger a pipeline run in ZenML by providing a pipeline name, snapshot, or stack override. Start the latest or a specific snapshot execution.

Instructions

Trigger a pipeline to run from the server.

Args:
    pipeline_name_or_id: Optional name or ID of the pipeline to trigger. A
        snapshot or template can be triggered without it.
    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 template-based trigger parameter. Use
        `snapshot_name_or_id` for new integrations. ZenML 0.96.4 still
        retains run-template CRUD APIs.

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(
        snapshot_name_or_id=<SNAPSHOT_NAME_OR_ID>
    )
    ```
    * Run a specific template (DEPRECATED - use snapshot_name_or_id instead):
    ```python
    trigger_pipeline(template_id=<ID>)
    ```

Input Schema

TableJSON Schema

Name	Required	Description	Default
`template_id`	No
`stack_name_or_id`	No
`pipeline_name_or_id`	No
`snapshot_name_or_id`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv2.0.0Sep 23, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / pipeline_name_or_id / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / pipeline_name_or_id / default
```
Added value: +null
```
removedInput schema / properties / pipeline_name_or_id / type
```
Removed value: -"string"
```

removedInput schema / required

Removed value: -[
-  "pipeline_name_or_id"
-]

addedOutput schema / additionalProperties
```
Added value: +true
```

removedOutput schema / properties

Removed value: -{
-  "result": {
-    "title": "Result",
-    "type": "string"
-  }
-}

removedOutput schema / required
```
Removed value: -[
-  "result"
-]
```

changedOutput schema / title

Previous value: -"trigger_pipelineOutput"New value: +"trigger_pipelineDictOutput"

First observedv1.2.0Jan 22, 2026

TDQS

A4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description must carry all behavioral disclosure. It states the tool triggers a run 'from the server' but does not say whether the call blocks until completion, what side effects are created (a new pipeline run), or what authentication/configuration is required. For an action that starts a run, this is a meaningful omission.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with an Args block and four usage examples, but it is longer than necessary. The first two examples are nearly identical except for the stack override, and the content could be tightened without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given four optional parameters and no annotation support, the description provides enough parameter semantics, conditionals, and examples to call the tool correctly. The main gap is behavioral context (sync vs async, side effects), but the presence of an output schema partially covers return expectations. It is largely complete for invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema properties have no descriptions (0% coverage), so the description is the sole source of parameter meaning. It explains all four parameters, including the conditional relationship (pipeline_name_or_id optional if snapshot/template given), the preferred status of snapshot_name_or_id, and the deprecation of template_id, going well beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with "Trigger a pipeline to run from the server" — a specific verb and resource that tells the agent exactly what happens. It is clearly distinguished from sibling tools like zenml_list_resources or open_pipeline_run_dashboard because it is the only one about starting a run.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The Args section and usage examples explicitly describe when to use each parameter path: pipeline_name_or_id runs the latest runnable snapshot, snapshot_name_or_id runs a specific snapshot (RECOMMENDED), and template_id is marked DEPRECATED with a pointer to snapshot_name_or_id. This is strong internal guidance, though it does not contrast with sibling tools or mention prerequisites like needing a server connection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server