A
licenseA
qualityA
maintenanceMCP server that connects an AI assistant to a running ComfyUI instance, allowing it to fetch saved workflows, inject a prompt and seed, run generation, and return the image inline in chat.
2
GPL 3.0
local-comfyui-mcp
by pytraveler
Related Servers
Alternatives to local-comfyui-mcp
No user-submitted related servers found.
Related Servers
- AlicenseBqualityBmaintenanceAn MCP server that bridges AI agents with ComfyUI for automated workflow building, execution, monitoring, and output routing.961MIT
- AlicenseAqualityCmaintenanceA universal MCP server that lets agents discover ComfyUI nodes, build/edit/run API workflows, manage queues, retrieve outputs, and optionally render graphs on a ComfyUI canvas.232Apache 2.0
- AlicenseAqualityAmaintenanceThe MCP server that drafts ComfyUI workflows a human can actually read. It lets coding agents build, repair, port, validate, and run ComfyUI workflows against your own ComfyUI instance, delivering clean, organized, fully-labeled workflows.292MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that enables AI agents to control a local ComfyUI instance for image generation, allowing workflow understanding, parameter modification, execution, and model discovery.17 npm3Apache 2.0
- FlicenseNot gradedqualityDmaintenanceMCP server that connects local ComfyUI to AI agents, enabling natural language control of ComfyUI for creating workflows, generating images, and managing the queue.-
TDQS
A3.6/5.0
Scored across 64 tools
Disambiguation4/5
Most tools target a distinct resource and action, and the descriptions sharply distinguish likely confusions such as workspace vs workflow, run_workspace vs run_workflow, and get_progress vs get_download_progress. However, with 64 tools in related clusters like layout/arrange/align and install/update/repair/stage, an agent still needs careful reading to select reliably.
Naming Consistency2/5
Names are mostly snake_case, but conventions vary widely: verb_noun (get_workspace_graph, list_models), noun_verb (workspace_status, comfy_start), bare verbs (interrupt, free_memory), and inconsistent workspace/comfy prefixes. No single predictable pattern spans the set.
Tool Count1/5
64 tools is an extreme mismatch for a single MCP server surface, exceeding the 50+ tools threshold. Even if the domain is broad, the count imposes a heavy selection and maintenance burden.
Completeness4/5
The set covers workflow, live workspace, environment, package, extension, model, download, and logging operations, including install, update, repair, checkpoint, restore, and run lifecycles. Minor gaps remain, such as uninstalling an extension or deleting models/workflow files, but core workflows are well supported.
Maintenance
ActivityMaintained
ResponsivenessNo issues