ComfyUI
This ComfyUI MCP server integrates the ComfyUI stable diffusion interface with AI assistants. It provides a streamlined API for generating images using ComfyUI's node-based workflow, abstracting away the complexities of the underlying system. The server enables AI to construct image generation pipelines, adjust parameters, and retrieve results programmatically. By connecting AI systems with ComfyUI's powerful image generation capabilities, this implementation allows for dynamic creation of visual content based on textual descriptions or other inputs. It is particularly useful for applications requiring on-demand image generation, such as content creation tools, design assistants, or any AI system that needs to produce custom visuals.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/jonpojonpo/comfy-ui-mcp-server
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve ComfyUI from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.