Schema | fvtt-mcp-artificer

fvtt-mcp-artificer

Describes the environment variables required to run the server.

Name	Required	Description	Default
`COMFY_URL`	No	The headless ComfyUI instance URL.	http://127.0.0.1:8188
`COMFY_OUTPUT_DIR`	Yes	Must match the --output-directory ComfyUI was launched with; the server reads generated PNGs straight off this path.
`ARTIFICER_TIMEOUT_MS`	No	Per-job wait cap for ComfyUI jobs.	300000

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
generate-imageA	Generate Foundry table art with the local ComfyUI instance. Returns absolute PNG paths — read them to curate. Draft batches are ~2 s/image; final renders arrive finished at the preset output resolution (upscale pipeline included).
upscale-imageA	Run an existing image through the model-upscale pipeline to its kind’s finished resolution. Use on a draft that won curation as-is. Returns the finished PNG path.
artificer-statusA	Health check: ComfyUI reachability/version, VRAM, queue depth, pinned-workflow integrity, and required-model presence. Call this first when generation misbehaves.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Txpple/fvtt-mcp-artificer'

If you have feedback or need assistance with the MCP directory API, please join our Discord server