Comfyui MCP logo

Comfyui MCP

未认领

作者:hybridindie

Secure MCP server for ComfyUI — workflow inspection, path sanitization, rate limiting, and audit logging. Generate images from Claude and other AI assistants with built-in security controls.

ai-toolsclaudecomfyuiimage-generationmcpmcp-servermodel-context-protocolpythonsecuritystable-diffusion

安装

$uv --directory /path/to/comfyui_mcp run comfyui-mcp-secure

此服务器需要专门配置。目前没有可复用的公开启动命令,请遵循项目说明。

项目说明

更多Security服务器

浏览完整目录

未认领列表

这个 MCP 服务器是你的吗?

此列表根据公开信息自动生成。认领后,你可以编辑页面、设置兼容性并解锁增长工具。全程不超两分钟。

认领此服务器

安全概况

已认领和已认证的服务器每周接受一次静态扫描,显示代码能触及的范围(外部服务、环境变量、shell 命令、代理配置目录)以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理

40 个工具中显示 40 个

文档中列出的工具 (40)

内容来自项目文档。服务器握手不会验证每个工具的说明或行为。

comfyui_analyze_workflow

Return a structured analysis of a workflow as a dict (nodecount, classtypes, flow, models, parameters, pipeline, promptnodes, negativenodes). Use this when you want to read fields like pipeline programmatically; use comfyuisummarizeworkflow for a human-readable text or Mermaid rendering.

comfyui_audit_dangerous_nodes

Scan all installed nodes to identify potentially dangerous ones.

comfyui_cancel_job

Cancel a running or queued job. Uses the native /api/jobs/{id}/cancel endpoint and falls back to the legacy /queue delete on 404 (older ComfyUI builds).

comfyui_cancel_jobs

Batch-cancel one or more jobs by promptid via /api/jobs/cancel.

comfyui_clear_queue

Clear pending and/or running items from the queue.

comfyui_create_workflow

Create a workflow from templates including txt2img/img2img/upscale/inpaint, txt2vidanimatediff/txt2vidwan, controlnetcanny/controlnetdepth/controlnetopenpose, ipadapter, lorastack, facerestore, fluxtxt2img, and sdxltxt2img.

comfyui_generate_image

Text-to-image using a built-in workflow. Params: prompt, negativeprompt, width, height, steps, cfg, model. Set wait=True to block until complete and return outputs.

comfyui_get_job

Look up a single job (queued/running/finished) by promptid.

comfyui_get_model_metadata

Get metadata for a specific model file.

comfyui_get_model_preview

Fetch a model's preview image via /experiment/models/preview/{folder}/{pathindex}/{filename}. Returns base64-encoded image data + mime type, or {"available": false} on 404.

comfyui_get_node_info

Get detailed info about a specific node type.

comfyui_get_progress

Get execution progress for a workflow by promptid. Returns status, queue position, and outputs.

comfyui_get_queue

Get current execution queue state.

comfyui_get_queue_status

Get detailed queue status including running and pending prompts.

comfyui_get_server_features

Get ComfyUI server features and capabilities.

comfyui_get_settings

Read ComfyUI server settings (sampler defaults, UI prefs, feature flags) from GET /settings.

comfyui_get_subgraph

Fetch a single subgraph's JSON for inspection or insertion (/globalsubgraphs/{id}).

comfyui_get_system_info

Sanitized GPU VRAM, queue depth, and ComfyUI version (whitelist-filtered from /systemstats).

comfyui_inpaint_image

Inpaint masked regions of an image. Params: image, mask (filenames), prompt, negativeprompt, strength, steps, cfg, model. Both files must be uploaded first.

comfyui_install_custom_node

Queue install for a custom node pack by nodeid; optional restart and post-install security audit.

comfyui_interrupt

Interrupt the running workflow (global, or targeted via optional promptid).

comfyui_list_extensions

List available ComfyUI extensions.

comfyui_list_jobs

List jobs across queue + history with status filter, sorting, and pagination.

comfyui_list_model_folders

List available model folder types.

comfyui_list_models

List available models by folder (checkpoints, loras, vae, etc.).

comfyui_list_models_detailed

List models in a folder with file metadata (name, pathIndex, modified, created, size) from /experiment/models/{folder}. Use this when you need the pathIndex for preview lookups.

comfyui_list_nodes

List all available node types.

comfyui_list_subgraphs

List available reusable subgraph templates from ComfyUI (/globalsubgraphs).

comfyui_list_workflows

List saved workflow templates.

comfyui_modify_workflow

Apply batch operations (addnode, removenode, setinput, connect, disconnect) to a workflow.

comfyui_run_workflow

Submit arbitrary ComfyUI workflow JSON. Inspected for dangerous nodes before execution. Set wait=True to block until complete and return outputs.

comfyui_run_workflow_stream

Submit workflow JSON and capture ComfyUI websocket stream events (progress, executing, executed, etc.) until terminal status, returning events plus final outputs/status.

comfyui_search_custom_nodes

Search ComfyUI Manager registry custom node packs by name/description/author.

comfyui_summarize_workflow

Summarize a workflow's structure, data flow, models, and parameters. Supports outputformat="text" (default) or outputformat="mermaid" for diagram markup.

comfyui_transform_image

Image-to-image transformation. Params: image (filename), prompt, negativeprompt, strength (0.0-1.0), steps, cfg, model. Input must be uploaded via comfyuiuploadimage first.

comfyui_uninstall_custom_node

Queue uninstall for a custom node pack by nodeid; optional restart.

comfyui_update_custom_node

Queue update for a custom node pack by nodeid; optional restart and post-update security audit.

comfyui_update_settings

Merge new settings into the ComfyUI server config via POST /settings (audit-logged; mutating).

comfyui_upscale_image

Upscale an image using a model-based upscaler. Params: image (filename), upscalemodel (default: RealESRGANx4plus.pth).

comfyui_validate_workflow

Validate workflow structure, server compatibility, and security.

工具变更历史

比较相同配置的完整检查。只列出工具,未调用工具。此处不测量输入结构的变化。

尚无完整工具检查。