RunComfy MCP

Official

Overview Schema Source Related Servers Discussions Admin

get_training_job_result

Read-onlyIdempotent

Fetch training job artifacts as hosted URLs for checkpoints, config, and samples. Use during or after job completion to recover outputs and feed checkpoints to run_model for inference.

Instructions

Fetch a training job's artifacts as hosted URLs.

Backs ``GET /prod/v1/trainers/ai-toolkit/jobs/{job_id}/result``.
Returns checkpoints (``.safetensors``), the resolved config, and
sample outputs. Safe to call while the job is still ``RUNNING`` —
the artifact list grows over time — and after a ``FAILED`` or
``CANCELED`` job to recover whatever was produced.

Feed a checkpoint URL to ``run_model`` as
``{"lora": {"path": "<url>"}}`` to run inference on it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "job_id": "<job_id>"
    },
    "name": "get_training_job_result"
  }
}

Input Schema

Name	Required	Description	Default
`job_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Sep 7, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds meaningful behavioral context by explaining that results grow over time during execution and that partial artifacts remain available after failure or cancellation, which is not inferable from the annotations alone.

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

Conciseness5/5

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

The description is compact and front-loaded: the core action appears first, followed by return contents, lifecycle timing, and a practical usage example. Every sentence adds useful information without repeating the schema or annotations.

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

Completeness5/5

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

For a single-parameter read-only tool with no output schema, the description covers what is returned, when it is safe to call, and how to consume the result downstream. An agent has enough information to select and invoke the tool correctly.

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

Parameters3/5

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

The input schema has only job_id with 0% description coverage. The description adds context by embedding job_id in the endpoint URL and framing it as the ID of a training job, but it does not describe how to obtain it or any format constraints. The parameter is self-descriptive enough for a minimum viable score, but the description does not compensate richly for the schema gap.

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 a specific verb and resource: 'Fetch a training job's artifacts as hosted URLs.' It then enumerates what is returned (checkpoints, resolved config, sample outputs), making the tool's purpose unmistakable and clearly distinct from sibling status or cancellation tools.

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 description explicitly says when it is safe to call: while the job is RUNNING (artifact list grows over time) and after FAILED or CANCELED jobs to recover produced artifacts. It also gives downstream usage guidance by explaining how to feed a checkpoint URL to run_model. It does not explicitly contrast against get_training_job_status, but the usage context is clear.

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