Skip to main content
Glama
Sign In
mike-nott

comfy-mcp

by mike-nott
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to comfy-mcp

No user-submitted related servers found.

    Related Servers

    • Numera Image-Gen MCP

      KiaroSama
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables local, provider-independent image generation and editing through named connections, multiple image protocols, and configured ComfyUI workflows, with saved outputs, job tracking, and explicit tool operations.
      3
      GPL 3.0

    • ComfyUI Local MCP Server

      AkiraVD
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP clients to generate and edit images using local Stable Diffusion models in ComfyUI, with tools for text-to-image, img2img, ControlNet, UI frames, upscaling, and background removal—no cloud API or API key required.
      MIT

    • comfy-image-mcp

      anechunaev
      A
      license
      A
      quality
      C
      maintenance
      Turns your own ComfyUI workflows into an image-generation tool for any MCP client, enabling text-to-image generation, reference-image edits, transparent-background cutouts, and backend/GPU status checks without API keys or per-image costs.
      2
      MIT

    • comfyui-roundabout

      0c0
      A
      license
      Not graded
      quality
      C
      maintenance
      Exposes ComfyUI workflows as 12 MCP tools on ComfyUI's own port, letting AI agents generate, edit, and remove backgrounds from images plus create videos by passing semantic parameters instead of whole workflow graphs. Agents can list models, submit and track async tasks, fetch artifact URLs, and jump to a visual asset/task page.
      3
      MIT
    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

    A4.2/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool targets a distinct concern: generation, editing, server/model inspection, and job lifecycle management. The job-related tools (status, wait, fetch, cancel) are clearly differentiated by their blocking behavior and return payload.

    Naming Consistency4/5

    Most tools follow a clear verb_noun pattern: generate_image, edit_image, list_models, fetch_result, cancel_job. The two status tools (server_status, job_status) are noun-first, which is a minor deviation but still readable and internally consistent.

    Tool Count5/5

    Eight tools is well-scoped for an image generation/editing server with asynchronous job support. Each tool serves a clear purpose without redundancy or bloat.

    Completeness5/5

    The surface covers the full generation/edit workflow plus model discovery, server health, and complete job lifecycle management (status, wait, fetch, cancel). No critical operations are missing for the stated domain.

    Maintenance

    ActivitySlowing
    ResponsivenessNo issues

    Resources