
Cursor
Desktop · Freemium · Proprietary
The first agentic IDE. The Cursor editor truly merges how developers and AI work together, delivering a magical coding experience.
Developer Tools · Image & Video

joenorton/comfyui-mcp-server
A lightweight MCP (Model Context Protocol) server that lets AI agents generate and iteratively refine images, audio, and video using a local ComfyUI instance.
See repository
Setup steps are in the repository README.
Iterative refinement via regenerate (no re-prompting)
Explicit asset identity for reliable follow-ups
Job polling and cancellation for long-running generations
Optional image injection into the AI’s context (view_image)
Auto-discovered ComfyUI workflows with parameter exposure
Configurable defaults to avoid repeating common settings
generate_image
Generate images (requires prompt)
generate_song
Generate audio (requires tags and lyrics)
regenerate
Regenerate an existing asset with optional parameter overrides (requires asset_id)
view_image
View generated images inline (images only, not audio/video)
get_queue_status
Check ComfyUI queue state (running/pending jobs) - provides async awareness
get_job
Poll job completion status by prompt_id - check if a job has finished
list_assets
Browse recently generated assets - enables AI memory and iteration
get_asset_metadata
Get full provenance and parameters for an asset - includes workflow history
cancel_job
Cancel a queued or running job
get_defaults
Get current default values
set_defaults
Set default values (with optional persistence)
run_workflow
Run any workflow with custom parameters
get_publish_info
Show publish status (detected project root, publish dir, ComfyUI output root, and any missing setup)
set_comfyui_output_root
Set ComfyUI output directory (recommended for Comfy Desktop / nonstandard installs; persisted across restarts)
publish_asset
Publish a generated asset into the project's web directory with deterministic compression (default 600KB)
Session-scoped
asset_ids are valid only for the current server session; restart invalidates them.
Manifest
Updated only when manifest_key is provided.
Compression
Deterministic ladder to meet size limits; fails with a clear error if it can't.
Details on this page are taken from the project's README. Open README
Clients mentioned in this server's README:

microsoft/playwright
Playwright is a framework for web automation and testing. It drives Chromium, Firefox, and WebKit with a single API — in your tests, in your scripts, and as a tool for AI agents.

yamadashy/repomix
Repomix is a tool that packs a codebase into an AI-friendly format, supporting local and remote repository processing and providing code compression, security checks and multiple output formats.

bytedance/UI-TARS-desktop
TARS is ByteDance's multimodal AI agent stack, shipping two projects: Agent TARS (a CLI and Web UI agent built on MCP) and UI-TARS-desktop (a desktop GUI agent).

ahujasid/blender-mcp
formerly blender-mcp — the PyPI package is now mcp-for-blender. Existing setups keep working; no config change is required. Read more.

microsoft/playwright-mcp
A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.

comet-ml/opik
Opik is the open-source LLM observability and evaluation platform for AI agent tracing, LLM evaluation, prompt management, and production monitoring. Built by Comet. Apache-2.0 licensed, free to self-host the full platform, with 20,000+ GitHub stars.