Schema | comfyui-mcp

comfyui-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`comfyui.host`	No	ComfyUI host and port	127.0.0.1:8188
`comfyui.request_timeout`	No	Timeout in seconds for ComfyUI API requests	5
`comfyui.workflow_directory`	No	Local directory path for workflow JSON files	workflows
`comfyui.use_remote_workflow`	No	Pull workflows from ComfyUI API (True) or load from local directory (False)	True
`generate.audio_url_template`	No	Template for audio output URLs (vars: {index}, {url})
`generate.image_url_template`	No	Template for image output URLs (vars: {index}, {url})
`generate.unknown_url_template`	No	Template for unknown output types (vars: {index}, {url})
`generate.reply_include_workflow`	No	Include executed workflow parameters in response	True
`generate.reply_workflow_template`	No	Template for workflow parameters section (vars: {workflow_params})
`generate.nothing_generated_message`	No	Message when workflow executes but produces no output
`generate.reply_workflow_format_indent`	No	JSON indentation for workflow output	2
`generate.reply_workflow_format_sort_keys`	No	Sort JSON keys in workflow output	True
`generate.result_generated_message_template`	No	Overall message template (vars: {image_list})

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityInactive

ResponsivenessNo issues