comfy-draftsman
Related Servers
Alternatives to comfy-draftsman
No user-submitted related servers found.
Related Servers
- 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
- AlicenseBqualityBmaintenanceAn MCP server that bridges AI agents with ComfyUI for automated workflow building, execution, monitoring, and output routing.961MIT
- 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
- AlicenseAqualityCmaintenanceMCP server that lets AI agents drive a remote ComfyUI instance end-to-end, including queueing workflows, viewing outputs, downloading models, and authoring graphs via ComfyScript.1643,648 npmMIT
- 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.-
- AlicenseAqualityAmaintenanceAn MCP server that integrates with a local ComfyUI, allowing assistants to list and run workflows, monitor progress, and view results, as well as read and edit the live workflow canvas via an optional bridge node.6412GPL 3.0
TDQS
Scored across 29 tools
Most tools have clearly separated roles: instance introspection, node/module discovery, workflow editing, workflow checking, execution, output handling, and queue management. A few pairs like get_instance_info/check_setup and lint_workflow/validate_workflow/diagnose_workflow are close enough to require careful reading, but they are not interchangeable.
Every tool uses clear, predictable snake_case verb_noun naming: get_, list_, create_, import_, edit_, run_, save_, search_, and manage_ are applied consistently. The many *workflow tools all share the same suffix pattern, and there are no mixed conventions or vague verbs.
At 29 tools, this is a heavy toolset, but the count maps fairly well to the broad ComfyUI lifecycle: setup, discovery, workflow creation/editing, validation/repair, execution, output retrieval, queue control, and persisted knowledge. It is slightly over-scoped, with a few validation/status/output tools that could theoretically be merged, but the count is not bloated given the domain.
The surface is nearly complete for a ComfyUI drafting assistant: one can discover nodes/models/templates, create and import workflows, edit and organize them, validate or diagnose them, run them, fetch outputs, upload images, manage the queue, and save or export the result. The main missing lifecycle niceties are explicit workflow deletion and uninstall/manage node packs, which are minor gaps rather than dead ends.