ComfyUI
This MCP server implementation provides a bridge to ComfyUI, a powerful UI for Stable Diffusion workflows. Developed by Karim Lalani, it enables AI assistants to generate images using custom ComfyUI workflows through natural language prompts. The server utilizes a JSON-defined workflow and integrates with the ComfyUI API, allowing for flexible image generation pipelines. It's particularly useful for AI-assisted creative tasks, prototyping visual concepts, and integrating advanced image generation capabilities into AI applications. The implementation focuses on ease of use and configurability, supporting customizable workflow parameters and seamless integration with Open WebUI.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
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/lalanikarim/comfy-mcp-pipeline
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
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.