Skip to main content
Glama
runcomfy-com

RunComfy MCP

Official
by runcomfy-com
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to RunComfy MCP

No user-submitted related servers found.

    Related Servers

    • ComfyUI MCP Server

      vovchanskuy2
      F
      license
      Not graded
      quality
      B
      maintenance
      MCP server that exposes ComfyUI image and 3D generation as a single tool with smart prompt classification. It enables AI assistants to generate assets directly by selecting and running the appropriate ComfyUI workflow.
      -

    • comfyui-mcp

      GermaniU
      A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that wraps ComfyUI for SDXL image generation. It exposes tools for generating images, listing models, and checking ComfyUI health, with presets and GPU resource coordination.
      MIT

    • ComfyUI MCP Skills

      ShiroEirin
      A
      license
      B
      quality
      B
      maintenance
      MCP server that dynamically exposes each enabled ComfyUI workflow as a tool with JSON Schema, supports job submission with wait and idempotency, file uploads, and resource metadata, with both stdio and authenticated Streamable HTTP transports.
      3
      5
      MIT

    • comfy-mcp

      cuzelac
      A
      license
      Not graded
      quality
      D
      maintenance
      MCP server that enables AI agents to control a local ComfyUI instance for image generation, allowing workflow understanding, parameter modification, execution, and model discovery.
      23 npm
      3
      Apache 2.0
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4/5.0

    Scored across 31 tools

    Disambiguation4/5

    Tools are grouped by resource with clear action prefixes, so deployments, datasets, models, and training jobs are generally easy to tell apart. The main ambiguity risk is the parallel request-status/result/cancel tools for deployment requests versus model API requests, which require careful reading to avoid misselection.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern, e.g., create_deployment, list_datasets, submit_training_job, cancel_model_request. Even longer names like upload_dataset_file_from_url and get_dataset_upload_urls stay predictable and readable.

    Tool Count2/5

    At 31 tools, this is a heavy surface and exceeds the 25+ threshold for too many tools. The tools are well organized into deployment, dataset, model, and training clusters, but the MCP would be easier to navigate if split into separate per-domain servers.

    Completeness4/5

    Core platform workflows are well covered: deployment CRUD plus inference lifecycle, model discovery and execution, dataset creation and upload, and training job submission/status/result/cancel/resume/edit. The notable gaps are the lack of a list_training_jobs tool and no way to list past requests, though agents can work around these by capturing IDs from submission calls.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources