# io.github.zenml-io/mcp-zenml (oci · docker.io/zenmldocker/mcp-zenml)

MCP server for discovering, reading, and changing ZenML resources with compact generic tools

- Trust score: 41/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- oci · `docker.io/zenmldocker/mcp-zenml`: 41/100 (this document), [markdown](https://verifymcp.io/servers/zenml-io-mcp-zenml/docker-io-zenmldocker-mcp-zenml.md), [page](https://verifymcp.io/servers/zenml-io-mcp-zenml/docker-io-zenmldocker-mcp-zenml)

## Channel facts

- Registry: `oci`
- Package: `docker.io/zenmldocker/mcp-zenml`
- Version: `2.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1913 tokens (~95/item across 20 items; 16 tools + 4 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.zenml-io/mcp-zenml server?

io.github.zenml-io/mcp-zenml runs locally as a container image, launched with docker run --rm -i -e ZENML_STORE_URL -e ZENML_STORE_API_KEY -e ZENML_MCP_PROFILE -e ZENML_MCP_WRITE_POLICY docker.io/zenmldocker/mcp-zenml:2.1.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add zenml-io-mcp-zenml -- docker run --rm -i -e ZENML_STORE_URL -e ZENML_STORE_API_KEY -e ZENML_MCP_PROFILE -e ZENML_MCP_WRITE_POLICY docker.io/zenmldocker/mcp-zenml:2.1.0
```

This image reads ZENML_STORE_URL, ZENML_STORE_API_KEY, ZENML_MCP_PROFILE and ZENML_MCP_WRITE_POLICY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Cursor

```json
{
  "mcpServers": {
    "zenml-io-mcp-zenml": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "ZENML_STORE_URL",
        "-e",
        "ZENML_STORE_API_KEY",
        "-e",
        "ZENML_MCP_PROFILE",
        "-e",
        "ZENML_MCP_WRITE_POLICY",
        "docker.io/zenmldocker/mcp-zenml:2.1.0"
      ]
    }
  }
}
```

This image reads ZENML_STORE_URL, ZENML_STORE_API_KEY, ZENML_MCP_PROFILE and ZENML_MCP_WRITE_POLICY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### VS Code

```json
{
  "servers": {
    "zenml-io-mcp-zenml": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "ZENML_STORE_URL",
        "-e",
        "ZENML_STORE_API_KEY",
        "-e",
        "ZENML_MCP_PROFILE",
        "-e",
        "ZENML_MCP_WRITE_POLICY",
        "docker.io/zenmldocker/mcp-zenml:2.1.0"
      ]
    }
  }
}
```

This image reads ZENML_STORE_URL, ZENML_STORE_API_KEY, ZENML_MCP_PROFILE and ZENML_MCP_WRITE_POLICY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Codex

```bash
codex mcp add zenml-io-mcp-zenml -- docker run --rm -i -e ZENML_STORE_URL -e ZENML_STORE_API_KEY -e ZENML_MCP_PROFILE -e ZENML_MCP_WRITE_POLICY docker.io/zenmldocker/mcp-zenml:2.1.0
```

This image reads ZENML_STORE_URL, ZENML_STORE_API_KEY, ZENML_MCP_PROFILE and ZENML_MCP_WRITE_POLICY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "zenml-io-mcp-zenml": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "-e",
        "ZENML_STORE_URL",
        "-e",
        "ZENML_STORE_API_KEY",
        "-e",
        "ZENML_MCP_PROFILE",
        "-e",
        "ZENML_MCP_WRITE_POLICY",
        "docker.io/zenmldocker/mcp-zenml:2.1.0"
      ],
      "enabled": true
    }
  }
}
```

This image reads ZENML_STORE_URL, ZENML_STORE_API_KEY, ZENML_MCP_PROFILE and ZENML_MCP_WRITE_POLICY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Hermes

```yaml
mcp_servers:
  zenml-io-mcp-zenml:
    command: "docker"
    args: ["run", "--rm", "-i", "-e", "ZENML_STORE_URL", "-e", "ZENML_STORE_API_KEY", "-e", "ZENML_MCP_PROFILE", "-e", "ZENML_MCP_WRITE_POLICY", "docker.io/zenmldocker/mcp-zenml:2.1.0"]
```

This image reads ZENML_STORE_URL, ZENML_STORE_API_KEY, ZENML_MCP_PROFILE and ZENML_MCP_WRITE_POLICY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Netclaw

```json
{
  "McpServers": {
    "zenml-io-mcp-zenml": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "-e",
        "ZENML_STORE_URL",
        "-e",
        "ZENML_STORE_API_KEY",
        "-e",
        "ZENML_MCP_PROFILE",
        "-e",
        "ZENML_MCP_WRITE_POLICY",
        "docker.io/zenmldocker/mcp-zenml:2.1.0"
      ]
    }
  }
}
```

This image reads ZENML_STORE_URL, ZENML_STORE_API_KEY, ZENML_MCP_PROFILE and ZENML_MCP_WRITE_POLICY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Other

```json
{
  "mcpServers": {
    "zenml-io-mcp-zenml": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "ZENML_STORE_URL",
        "-e",
        "ZENML_STORE_API_KEY",
        "-e",
        "ZENML_MCP_PROFILE",
        "-e",
        "ZENML_MCP_WRITE_POLICY",
        "docker.io/zenmldocker/mcp-zenml:2.1.0"
      ]
    }
  }
}
```

This image reads ZENML_STORE_URL, ZENML_STORE_API_KEY, ZENML_MCP_PROFILE and ZENML_MCP_WRITE_POLICY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 41, +1)

- [functional regression] Security disclosure: unverified → fail

### 2026-11-03 (score 40, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-11-02 (score 40)

First indexed and scored.

## MCP tools (16)

### `diagnose_zenml_setup` (~69 tokens)

Diagnose ZenML MCP server setup (env vars, connectivity, auth, versions).

    Returns structured diagnostics about the server's configuration and
    connectivity. This tool works even when the ZenML SDK is not installed
    or environment variables are missing - use it to troubleshoot setup issues.

### `get_step_logs` (~270 tokens)

Get the logs for a specific step run.

    Returns ``{"logs": [...], "possibly_truncated": bool}`` with entries oldest
    first. At most 50,000 entries are returned. ``possibly_truncated`` is true
    when the step may have more log entries than were returned, and a ``note``
    then says which entries are missing and why. Pass ``tail``
    (for example 200) to get only the newest entries; that is usually where a
    failure shows up, and it keeps the response small. Log stores that can only
    read a log from its start (the default artifact store) return the newest of
    the first 50,000 entries for a longer log, with ``possibly_truncated`` set.

    Args:
        step_run_id: The ID of the step run to get logs for.
        source: Optional log source. Defaults to ZenML's ordinary ``step`` source.
        logs_id: Optional exact log record ID. Cannot be combined with ``source``.
        tail: Optional number of newest entries to return, from 1 to 50000.

Input parameters:

- `logs_id`
- `source`
- `step_run_id` (string, required)
- `tail`

### `zenml_describe_resources` (~74 tokens)

Discover supported generic ZenML resources or one operation schema.

    With no arguments this returns a short catalog. Pass a canonical singular
    resource type to inspect its operations, and add an operation name for its
    bounded input schema and a small example.

Input parameters:

- `operation`
- `resource_type`

### `zenml_list_resources` (~106 tokens)

List one allowlisted ZenML resource type with validated filters.

    Use ``zenml_describe_resources(resource_type, "list")`` to discover the
    accepted filters. Page sizes are capped at 200. Project-scoped reads use
    ``project_id`` when supplied and otherwise report the active project used.

Input parameters:

- `filters`
- `page` (integer)
- `project_id`
- `resource_type` (string, required)
- `size`

### `zenml_get_resource` (~99 tokens)

Get one allowlisted ZenML resource by its identifier.

    Artifact versions, model versions, and run steps require their parent
    identifier. Stack components require their fixed component type.

Input parameters:

- `artifact_id`
- `component_type`
- `hydrate`
- `model_id`
- `pipeline_run_id`
- `project_id`
- `resource_id` (string, required)
- `resource_type` (string, required)

### `zenml_create_resource` (~86 tokens)

Create one allowlisted ZenML resource with a strict typed payload.

    Inspect ``zenml_describe_resources(resource_type, "create")`` first.
    Project-scoped creates require an exact project UUID and never change the
    client's active project.

Input parameters:

- `model_id`
- `payload`
- `project_id`
- `resource_type` (string, required)

### `zenml_update_resource` (~67 tokens)

Update one exact UUID through an allowlisted operation-specific payload.

Input parameters:

- `artifact_id`
- `component_type`
- `model_id`
- `payload`
- `project_id`
- `resource_id` (string, required)
- `resource_type` (string, required)

### `zenml_delete_resource` (~66 tokens)

Delete or archive one exact UUID using bounded destructive options.

Input parameters:

- `artifact_id`
- `component_type`
- `model_id`
- `payload`
- `project_id`
- `resource_id` (string, required)
- `resource_type` (string, required)

### `zenml_action_resource` (~105 tokens)

Run one finite ZenML lifecycle or relation action.

    Inspect ``zenml_describe_resources(resource_type, "action")`` for the exact
    action names and payload schema. Every identifier must be an exact UUID.
    Actions may have effects outside the ZenML server and are never retried.

Input parameters:

- `action` (string, required)
- `payload`
- `project_id`
- `resource_id` (string, required)
- `resource_type` (string, required)

### `get_active_user` (~15 tokens)

Get the currently active user.

### `get_active_project` (~45 tokens)

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.

### `trigger_pipeline` (~336 tokens)

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. The supported ZenML
            version still retains run-template CRUD APIs.

        run_configuration: Optional ZenML run configuration overrides, including
            step parameters, substitutions, and cache settings. Validated by the
            ZenML SDK before triggering the run.

    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 parameters:

- `pipeline_name_or_id`
- `run_configuration`
- `snapshot_name_or_id`
- `stack_name_or_id`
- `template_id`

### `get_deployment_logs` (~160 tokens)

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:
        Dict with 'logs' (string) and metadata about truncation if applicable

Input parameters:

- `name_id_or_prefix` (string, required)
- `project`
- `tail` (integer)

### `get_step_code` (~42 tokens)

Get the code for a step.

    Args:
        step_run_id: The ID of the step to retrieve

Input parameters:

- `step_run_id` (string, required)

Output parameters:

- `result` (string)

### `open_pipeline_run_dashboard` (~63 tokens)

Open an interactive dashboard of recent ZenML pipeline runs.

    The dashboard shows pipeline runs with status indicators, expandable step
    details, filtering, and drill-down into step logs — all in an interactive UI.
    The dashboard fetches its own data dynamically.

Output parameters:

- `result` (string)

### `open_run_activity_chart` (~58 tokens)

Open an interactive chart showing pipeline run activity over the last 30 days.

    Shows a bar chart with daily run counts, hover tooltips, and status
    breakdown (completed in green, failed in red, other in amber).

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/zenml-io-mcp-zenml/docker-io-zenmldocker-mcp-zenml#diagnostics

## Score history

- 2026-11-05: 41
- 2026-11-04: 41
- 2026-11-03: 40
- 2026-11-02: 40

## Common questions

### What is the io.github.zenml-io/mcp-zenml server?

io.github.zenml-io/mcp-zenml is listed in the public MCP registry as io.github.zenml-io/mcp-zenml. MCP server for discovering, reading, and changing ZenML resources with compact generic tools. This page covers its container image (docker.io/zenmldocker/mcp-zenml).

### Is the io.github.zenml-io/mcp-zenml server safe to use?

io.github.zenml-io/mcp-zenml scores 41 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.zenml-io/mcp-zenml server expose?

io.github.zenml-io/mcp-zenml exposes 16 tools: diagnose_zenml_setup, get_step_logs, zenml_describe_resources, zenml_list_resources, zenml_get_resource, and 11 more. Their descriptions and schemas cost roughly 1,661 tokens of context every time the server is loaded.

### Is the io.github.zenml-io/mcp-zenml server still maintained?

io.github.zenml-io/mcp-zenml is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.zenml-io/mcp-zenml server under?

io.github.zenml-io/mcp-zenml declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the io.github.zenml-io/mcp-zenml server?

VerifyMCP ran 13 checks on io.github.zenml-io/mcp-zenml, covering Source repository, Provenance, License, Maintenance and 9 more. 4 items could not be completed, a gap on our side rather than a finding about io.github.zenml-io/mcp-zenml: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Docker Hub: https://hub.docker.com/r/zenmldocker/mcp-zenml
- Repository: https://github.com/zenml-io/mcp-zenml
- Changelog RSS feed: https://verifymcp.io/servers/zenml-io-mcp-zenml/docker-io-zenmldocker-mcp-zenml.xml
- Changelog JSON feed: https://verifymcp.io/servers/zenml-io-mcp-zenml/docker-io-zenmldocker-mcp-zenml/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/zenml-io-mcp-zenml/docker-io-zenmldocker-mcp-zenml.json
- HTML version of this page: https://verifymcp.io/servers/zenml-io-mcp-zenml/docker-io-zenmldocker-mcp-zenml