20 Best Image Generation MCP Servers, Compared (November 2026)

The short answer

Which one, for your situation

Top MCP servers for Image Generation

The ranking, with the evidence

• 1

  ComfyUI MCP

  Community favourite

  artokun/comfyui-mcp ↗

  Best for: When running a local ComfyUI install: it exposes 41 tools for workflow authoring, queue management, model downloads, VRAM control, and custom-node management.

  The server exposes 41 MCP tools for generating images, authoring and enqueueing ComfyUI workflows, inspecting queues and history, downloading models, clearing VRAM, and installing or managing custom nodes. It assumes a running ComfyUI installation and Node.js 22 or newer, and installs via npx as a standalone MCP server without cloning the repository.

  Score 85.2: show every number behind it

  • Adoption81 / 100 · weight 40%
    • GitHub stars74
    • npm downloads48
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum69 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute81
    • npm download trend0
  • Tool quality78 / 100 · weight 13%
    • Tool description quality70
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  85.2

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  85.2

• 2

  MeiGen AI Image Generation MCP

  Community favourite

  jau123/MeiGen-AI-Design-MCP ↗

  Best for: Ecommerce product imagery and marketing poster creation: it exposes tools for product detail images, posters, AI backgrounds, upscaling, and background removal.

  MeiGen AI Image Generation MCP exposes 18 tools for generating and editing images and videos, plus prompt enhancement, inspiration search, model and skill lookup, background removal, product detail images, posters, AI backgrounds, and upscaling. Before choosing it, note that MeiGen Cloud generation uses purchased credits and daily free credits do not apply.

  Score 82.0: show every number behind it

  • Adoption85 / 100 · weight 40%
    • GitHub stars81
    • npm downloads27
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum41 / 100 · weight 14%
    • Stars gained, relative to size42
    • Stars gained, absolute54
    • npm download trend23
  • Tool quality71 / 100 · weight 13%
    • Tool description quality63
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  82.0

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  82.0

• 3

  Smart Image Generator

  Community favourite

  shinpr/mcp-image ↗

  Best for: Generating or editing images from a coding assistant: one generate_image tool that rewrites short prompts into detailed ones before calling the image model.

  The server exposes a single generate_image tool that takes a text prompt or reference image paths, writes the result to a configured output directory, and returns it as an MCP resource. It requires Node.js 22 or later and an API key for Gemini by default, or for OpenAI or BytePlus Seedream if the provider is switched, and the prompt rewriting step can be turned off with SKIP_PROMPT_ENHANCEMENT.

  Score 75.6: show every number behind it

  • Adoption62 / 100 · weight 40%
    • GitHub stars57
    • npm downloads35
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance95 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence100
  • Momentum59 / 100 · weight 14%
    • Stars gained, relative to size96
    • Stars gained, absolute51
    • npm download trend0
  • Tool quality83 / 100 · weight 13%
    • Tool description quality75
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  75.6

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  75.6

• 4

  gflow-cli

  Community favourite

  ffroliva/gflow-cli ↗

  Best for: For an agent or terminal workflow using a Google Flow account: it exposes 19 MCP tools for Imagen generation, Veo video, upscaling, and credit checks.

  gflow-cli exposes 19 MCP tools for generating Imagen images and Veo videos from Google Flow, plus upscaling, character, project, instruction, and credit and auth status operations. It requires a local Google account with Flow access and a headed Playwright Chromium session, and video generations bill that account's credits.

  Score 67.8: show every number behind it

  • Adoption79 / 100 · weight 40%
    • GitHub stars64
    • PyPI downloads69
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum92 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute79
    • PyPI download trend93
  • Tool quality73 / 100 · weight 13%
    • Tool description quality65
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  86.9

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  67.8

• 5

  guaardvark

  Community favourite

  guaardvark/guaardvark ↗

  Best for: Running image generation and editing on a local NVIDIA GPU without cloud calls: it exposes generate_image, edit_image and get_generation_status tools.

  Guaardvark exposes 55 MCP tools for local image generation and editing, video and music-video generation, media playback, code and document search, and WordPress content generation. Its generation tools depend on the server's own GPU, and media playback and volume control are Linux only.

  Score 63.7: show every number behind it

  • Adoption64 / 100 · weight 40%
    • GitHub stars62
    • npm downloadsnot measured
      no npm package
    • Used through Glama14
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum88 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute69
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality83 / 100 · weight 13%
    • Tool description quality75
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  81.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  63.7

• 6

  MCP Image Generator (Uncensored)

  Emerging

  hypersniper05/MCP-Image-Generator-Uncensored ↗

  Best for: A local network needing uncensored image generation and editing: it serves Qwen-Image-2.1 over Streamable HTTP for text-to-image and multi-image edits.

  The server runs a self-hosted Qwen-Image-2.1 model over Streamable HTTP for MCP clients, with documented text-to-image, multi-image editing, transparent backgrounds, texture maps, 360 panoramas, upscaling, and watermark removal. Before choosing it, note that setup assumes Docker and an NVIDIA GPU for GPU use, while video generation is optional and requires the video extension.

  Score 62.3: show every number behind it

  • Adoption51 / 100 · weight 40%
    • GitHub stars51
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance95 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence100
  • Momentum85 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute62
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈70 / 100 · weight 13%
    • Tool description quality≈70
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  73.3

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  62.3

• 7

  AWS Nova Canvas

  Abandoned but popular

  awslabs/mcp ↗

  Best for: Creating mockups, diagrams, or UI design concepts: its generate_image and generate_image_with_colors tools generate images from prompts or color palettes.

  The server exposes 2 tools, generate_image for text-prompt image generation and generate_image_with_colors for color-guided image generation, and it documents saving generated images to user-specified workspace directories. It requires an AWS account with Amazon Bedrock and Nova Canvas enabled and AWS credentials configured through an AWS profile.

  Score 61.1: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars100
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance42 / 100 · weight 24%
    • Last commit touching this server42
      dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 0 days ago, which counts every ref
    • Repository maintenance gradenot measured
      repository is active but this server inside it is not
    • Commit cadencenot measured
      repository is active but this server inside it is not
  • Momentum64 / 100 · weight 14%
    • Stars gained, relative to size48
    • Stars gained, absolute87
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality81 / 100 · weight 13%
    • Tool description quality73
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  78.3

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  61.1

• 8

  dsh-crew

  Community favourite

  ZSeven-W/dsh-crew ↗

  Best for: Claude Code or Codex users needing vision and image generation through MCP: it documents `describe_image` and `generate_image` tools alongside DSH agent dispatch.

  DSH Crew is a DeepSeek Harness plugin that dispatches work to DSH agents from Claude Code, Codex, Antigravity, or Grok and documents describe_image and generate_image tools for vision and image generation. Before choosing it, note that image generation borrows the brush of installed Claude, Codex, Grok, or Antigravity CLIs.

  Score 60.7: show every number behind it

  • Adoption61 / 100 · weight 40%
    • GitHub stars57
    • npm downloads27
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum81 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute68
    • npm download trend61
  • Tool quality≈70 / 100 · weight 13%
    • Tool description quality≈70
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  77.8

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  60.7

• 9

  pixelle-mcp-Image-generation

  Abandoned but popular

  ATH-MaaS/Pixelle-MCP ↗

  Best for: ComfyUI users who want their workflows callable by MCP clients: it converts ComfyUI workflows into MCP tools and exposes an MCP endpoint.

  It provides an MCP endpoint, a Chainlit web interface, file service, and a workflow engine that converts ComfyUI workflows into MCP tools, with local ComfyUI or RunningHub cloud ComfyUI execution. Before use, it requires selecting either local ComfyUI or RunningHub as the execution engine and configuring at least one LLM provider.

  Score 57.6: show every number behind it

  • Adoption76 / 100 · weight 40%
    • GitHub stars76
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance25 / 100 · weight 24%
    • Last commit touching this server42
    • Repository maintenance grade5
    • Commit cadence5
  • Momentum21 / 100 · weight 14%
    • Stars gained, relative to size19
    • Stars gained, absolute23
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈70 / 100 · weight 13%
    • Tool description quality≈70
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  57.6

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  57.6

• 10

  ComfyUI MCP Server

  Abandoned but popular

  joenorton/comfyui-mcp-server ↗

  Best for: Iterative image refinement with a local ComfyUI instance: it exposes generate_image, regenerate, and view_image for asset follow-ups.

  It serves a streamable HTTP MCP endpoint and documents tools for image and audio generation, asset viewing, job polling and cancellation, defaults, workflow execution, and asset publishing. It assumes a separately installed and locally running ComfyUI instance as the execution backend.

  Score 57.2: show every number behind it

  • Adoption65 / 100 · weight 40%
    • GitHub stars65
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance32 / 100 · weight 24%
    • Last commit touching this server42
    • Repository maintenance grade30
    • Commit cadence5
  • Momentum38 / 100 · weight 14%
    • Stars gained, relative to size41
    • Stars gained, absolute33
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈70 / 100 · weight 13%
    • Tool description quality≈70
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  57.2

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  57.2

• 11

  nanobanana-mcp-server

  Community favourite

  zhongweili/nanobanana-mcp-server ↗

  Best for: Generating or editing images from natural-language prompts inside an MCP client: it exposes a generate_image tool, plus upload_file for inputs larger than 20MB.

  The server exposes four tools: generate_image for creating or editing images from prompts, upload_file for pushing local files through the Gemini Files API and returning a URI, show_output_stats for output-directory statistics, and maintenance for cleanup operations. It requires a Google Gemini API key in GEMINI_API_KEY, or, when NANOBANANA_AUTH_METHOD is set to vertex_ai, Google Cloud Application Default Credentials together with a GCP project and region.

  Score 56.3: show every number behind it

  • Adoption65 / 100 · weight 40%
    • GitHub stars65
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance93 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence65
  • Momentum33 / 100 · weight 14%
    • Stars gained, relative to size36
    • Stars gained, absolute29
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality78 / 100 · weight 13%
    • Tool description quality70
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  72.2

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  56.3

• 12

  remove-ai-watermarks

  Community favourite

  wiltodelta/remove-ai-watermarks ↗

  Best for: Cleaning AI provenance metadata and visible labels from your own generated images or videos: it exposes identify, remove, and batch tools.

  The server exposes identify, remove, and batch tools that report AI provenance signals and write cleaned copies of images or videos the user generated, with metadata-only, visible-label, and directory processing modes. It runs locally over stdio with uvx and is intended for content the user owns; the README notes that some jurisdictions restrict removing AI labels.

  Score 55.1: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars95
    • PyPI downloads70
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum59 / 100 · weight 14%
    • Stars gained, relative to sizenot measured
      no snapshot history yet
    • Stars gained, absolutenot measured
      no snapshot history yet
    • PyPI download trend59
  • Tool quality81 / 100 · weight 13%
    • Tool description quality73
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  91.8

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  55.1

• 13

  Sanity MCP Server

  Steady

  sanity-io/agent-toolkit ↗

  Best for: Sanity CMS projects needing agent access to content, schemas, releases, and image generation: the remote MCP endpoint at https://mcp.sanity.io provides that access.

  The README documents a remote HTTP MCP server at https://mcp.sanity.io that gives agents access to Sanity projects for content, datasets, releases, schemas, and agent rules, and the server description also lists image generation. Before choosing it, note that it requires OAuth authorization or a bearer token and a Sanity project.

  Score 54.0: show every number behind it

  • Adoption57 / 100 · weight 40%
    • GitHub stars57
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance86 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade55
    • Commit cadence85
  • Momentum55 / 100 · weight 14%
    • Stars gained, relative to size65
    • Stars gained, absolute40
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈70 / 100 · weight 13%
    • Tool description quality≈70
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  69.2

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  54.0

• 14

  MidjourneyMCP

  Steady

  AceDataCloud/MidjourneyMCP ↗

  Best for: For Midjourney image and video generation through AceDataCloud: it exposes 16 tools for imagine, transform, blend, edit, and video operations.

  MidjourneyMCP exposes 16 tools for Midjourney image and video generation through the AceDataCloud API, covering imagine, transform, blend, edit, describe, video generation, task tracking, and prompt utilities, and its README documents hosted OAuth, hosted API token, and local stdio connection routes. Before choosing it, note that all connection routes depend on AceDataCloud, with hosted OAuth or an API token, while local stdio still requires ACEDATACLOUD_API_TOKEN and calls that service.

  Score 45.5: show every number behind it

  • Adoption35 / 100 · weight 40%
    • GitHub stars31
    • PyPI downloads24
      PyPI downloads show no weekday rhythm; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance97 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence85
  • Momentum59 / 100 · weight 14%
    • Stars gained, relative to size66
    • Stars gained, absolute29
    • PyPI download trend83
  • Tool quality81 / 100 · weight 13%
    • Tool description quality73
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  65.0

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  45.5

• 15

  qiaomu-codex-imagegen

  Steady

  joeseesun/qiaomu-codex-imagegen ↗

  Best for: Choosing a style direction before generating: it suggests divergent directions from scenario presets, composes prompts, and returns image file paths with pixel dimensions.

  Run as an MCP server, CLI or Agent Skill, it documents suggest_directions, compose_prompt and catalog listing tools, returns the actual prompt alongside each image, and supports image-to-image editing from reference images. It assumes a working Codex image-generation backend underneath, and its presets and prompt rules are built around Chinese-language poster, cover and social formats.

  Score 44.4: show every number behind it

  • Adoption53 / 100 · weight 40%
    • GitHub stars53
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance83 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence40
  • Momentum54 / 100 · weight 14%
    • Stars gained, relative to size65
    • Stars gained, absolute37
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈70 / 100 · weight 13%
    • Tool description quality≈70
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  67.0

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  44.4

• 16

  gemini-webapi-mcp

  Steady

  AndyShaman/gemini-webapi-mcp ↗

  Best for: Generating and editing images without a Gemini API key: it authenticates with browser cookies from a signed-in Chrome session and exposes a generate/edit image tool.

  It exposes six tools covering image generation and editing, multi-turn text chat, file uploads for questions about images, PDFs and videos, and URL analysis of webpages and YouTube videos. Authentication is read from Chrome cookies, so it assumes

  Score 43.3: show every number behind it

  • Adoption45 / 100 · weight 40%
    • GitHub stars45
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance77 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade55
    • Commit cadence40
  • Momentum59 / 100 · weight 14%
    • Stars gained, relative to size74
    • Stars gained, absolute36
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality88 / 100 · weight 13%
    • Tool description quality80
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  65.3

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  43.3

• 17

  ComfyUI-APP-MCP

  Steady

  Lotus0614/ComfyUI-APP-MCP ↗

  Best for: AI assistants generating images from existing ComfyUI App Mode workflows: it wraps those workflows as MCP templates for parameter lookup, execution, and multi-step chaining.

  ComfyUI-APP-MCP is a ComfyUI custom node whose README documents MCP tools for listing and reading App Mode templates, running one or more templates, uploading images, and querying model folders. It assumes a running ComfyUI instance with App Mode workflows configured as templates and installation as a custom node, and no npm or PyPI package is published.

  Score 43.0: show every number behind it

  • Adoption38 / 100 · weight 40%
    • GitHub stars38
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance92 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence85
  • Momentum44 / 100 · weight 14%
    • Stars gained, relative to size56
    • Stars gained, absolute26
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈70 / 100 · weight 13%
    • Tool description quality≈70
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  61.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  43.0

• 18

  ComfyUI-AnimaTool

  Dormant

  Moeblack/ComfyUI-AnimaTool ↗

  Best for: Generating anime-style images from a chat client through ComfyUI: it documents an MCP server with native image display in Cursor and Claude chat windows.

  The README documents an MCP server and an HTTP API for generating anime-style images via ComfyUI and Anima models, plus MCP image display in Cursor and Claude chat windows. A running ComfyUI instance and the Anima UNET, Qwen3 CLIP, and VAE files in the corresponding ComfyUI model directories are required.

  Score 41.6: show every number behind it

  • Adoption54 / 100 · weight 40%
    • GitHub stars54
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance25 / 100 · weight 24%
    • Last commit touching this server42
      dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 224 days ago, which counts every ref; the stored date would have published 224 days ago
    • Repository maintenance grade5
    • Commit cadence5
  • Momentum23 / 100 · weight 14%
    • Stars gained, relative to size29
    • Stars gained, absolute16
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈70 / 100 · weight 13%
    • Tool description quality≈70
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  48.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  41.6

• 19

  Z-Image Studio

  Steady

  iconben/z-image-studio ↗

  Best for: Local text-to-image generation across NVIDIA, Apple Silicon, Linux AMD ROCm, Intel, or CPU: it exposes generate, list_models, and list_history over stdio, SSE, or Streamable HTTP.

  Z-Image Studio provides local text-to-image generation through a CLI, web UI, and MCP server, exposing the generate, list_models, and list_history tools over stdio, SSE, and Streamable HTTP. AMD GPU acceleration is limited to Linux ROCm builds, so Windows systems with AMD GPUs fall back to CPU.

  Score 40.9: show every number behind it

  • Adoption53 / 100 · weight 40%
    • GitHub stars53
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance92 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence85
  • Momentum0 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality73 / 100 · weight 13%
    • Tool description quality65
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  61.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  40.9

• 20

  local-comfyui-mcp

  Steady

  pytraveler/local-comfyui-mcp ↗

  Best for: Editing the ComfyUI workflow open in the browser, unsaved edits included: an optional bridge node lets an assistant read the live graph and change values.

  It exposes 64 tools for listing and describing workflow files, running them, following progress, fetching results and downloading models, alongside workspace tools that read and edit the live canvas through an optional bridge node. That bridge is a separate install into ComfyUI's custom_nodes, needs a ComfyUI restart, and needs a browser tab left open, without which every workspace_* tool fails.

  Score 40.8: show every number behind it

  • Adoption31 / 100 · weight 40%
    • GitHub stars31
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance90 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade100
    • Commit cadence85
  • Momentum42 / 100 · weight 14%
    • Stars gained, relative to size54
    • Stars gained, absolute24
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality73 / 100 · weight 13%
    • Tool description quality65
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  58.3

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  40.8

Questions people ask

Other comparisons

• Best Figma MCP servers
• Best Obsidian MCP servers
• Best YouTube MCP servers
• Best Jira MCP servers
• Best PostgreSQL MCP servers
• Best MySQL MCP servers
• Best GitHub MCP servers
• Best Notion MCP servers
• Best Linear MCP servers
• Best Discord MCP servers
• Best MongoDB MCP servers
• Best CRM MCP servers
• Best Payments MCP servers
• Best Ecommerce MCP servers
• Best Social Media MCP servers
• Best Browser Automation MCP servers
• Best Email MCP servers
• Best PDF MCP servers
• Best Kubernetes MCP servers
• Best Docker MCP servers
• Best AWS MCP servers
• Best Spreadsheets MCP servers
• Best SEO MCP servers
• Best Web Search MCP servers
• Best Web Scraping MCP servers
• Best Vector Database MCP servers
• Best Code Execution MCP servers
• Best Calendar MCP servers
• Best Observability MCP servers
• Best Speech & Transcription MCP servers
• Best Maps MCP servers
• Best Travel MCP servers
• Best Stock Market MCP servers
• Best Web Analytics MCP servers
• Best Memory MCP servers
• Best Documentation MCP servers
• Best Security MCP servers