comfyops-mcp

Overview Schema Source Related Servers Discussions Admin

comfy_models

List installed models, download models from Hugging Face with SHA-256 verification, check GPU VRAM, and verify system health for ComfyUI workflows.

Instructions

Manage local models, download from Hugging Face (hash-verified), and check GPU VRAM.

Return Format

{"success": bool, "models": [...], "download": {...}, "vram": {...}, "health": {...}}

Examples

comfy_models(operation="list_installed")
comfy_models(operation="check_vram", model_vram_gb=6.0)
comfy_models(operation="download", hf_repo="org/model", filename="m.safetensors",
             target="diffusion_models", sha256="<hash>")
comfy_models(operation="health")

Input Schema

TableJSON Schema

Name	Required	Description
`sha256`	No	Expected sha256 of the file (verified when provided).
`target`	No	ComfyUI model subdir (checkpoints, diffusion_models, loras, text_encoders, vae, upscale_models).
`hf_repo`	No	Hugging Face repo id for download (e.g. 'black-forest-labs/FLUX.1-schnell').
`filename`	No	File name within the repo for download.
`dest_name`	No	Optional destination filename (defaults to filename).
`operation`	Yes	Operation to perform.
`model_vram_gb`	No	Estimated VRAM for check_vram.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 15, 2026

TDQS

A3.7/5.0

Behavior3/5

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

With empty annotations, the description carries the behavioral disclosure burden. It mentions hash-verified downloads and the return format, but does not disclose that downloads write to local disk, require network access, or that other operations are read-only. This is not misleading, but it is incomplete.

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 well-organized into summary, return format, and examples. Every line earns its place, with no redundant prose.

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 7 parameters and 4 operations, the description provides a return format and concrete examples for every operation, which is sufficient for an agent to invoke the tool correctly. It doesn't detail error behavior or sub-object fields, but the output schema is present and the examples cover the main gap.

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

Parameters4/5

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

All parameters have schema descriptions (100% coverage), so baseline is 3. The examples add value by showing which parameters apply to each operation (e.g., model_vram_gb for check_vram, hf_repo/filename/target/sha256 for download), exceeding baseline.

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

Purpose4/5

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

The description clearly states the tool's resource (local models) and key actions (manage, download from Hugging Face, check GPU VRAM), and the operation enum plus examples further pin down the scope. It does not explicitly differentiate from siblings like comfy_library, so it misses the top score.

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

Usage Guidelines3/5

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

Examples show valid invocations for each operation, which gives implicit usage guidance. However, there is no explicit statement about when to use this tool vs. alternatives such as comfy_generate or comfy_library, nor any exclusions.

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

Deploy Server