FRENES

Design, art and accessibility · MCP server

Runcomfy MCP: MCP server, setup and security

Runcomfy MCP is an open-source MCP server published on GitHub that lets an AI agent manage ComfyUI deployments, hosted model inference and LoRA training jobs. Its repository has 1 stars and its last commit is from September 15, 2026 and it is licensed under MIT.

OfficialActively maintainedRemote server

What Runcomfy MCP does

According to its repository: “Manage RunComfy ComfyUI serverless deployments, hosted model inference and LoRA training jobs.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Runcomfy MCP is listed under Design, art and accessibility, a category of 95 servers in the directory, where it ranks #89 by stars.

Topics declared by the repository: comfyui, gpu, image-generation, runcomfy, serverless, video-generation.

Installing and connecting Runcomfy MCP

Distribution modes declared in the official MCP registry:

  • remote server (streamable-http): you connect to it by URL, with nothing to install locally

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: Python.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Runcomfy MCP. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on July 14, 2026, the runcomfy-com/runcomfy-mcp repository has 1 stars and 3 forks, with 1 open issues. It has more stars than 7% of the servers in the directory. Last change 1 month ago. Version published in the registry: 1.1.0 (September 7, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

Next AI Draw.ioNext AI Draw.io : 36.4K36.4KPascal 3D EditorPascal 3D Editor : 25.1K25.1KDavinci resolve MCPDavinci resolve MCP : 3.7K3.7KFigma MCP ServerFigma MCP Server : 2.1K2.1KMeiGen AI Design MCPMeiGen AI Design MCP : 1.8K1.8KTerraVisionTerraVision : 1.7K1.7KMeasureMeasure : 1.4K1.4KFigwrightFigwright : 1.2K1.2KRuncomfy MCPRuncomfy MCP : 11
GitHub stars of the most followed servers in the category (log scale); Runcomfy MCP in orange. Checked October 25, 2026.

Verdict

Runcomfy MCP is a reasonable choice; check the points below before connecting it.

Strengths

  • Maintained by the service's own vendor
  • Active project: recent commit
  • Listed in the official MCP registry
  • Usable remotely, without installation
  • Permissive licence (MIT)

Limitations

  • Few visible users

Frequently asked questions

How do I install Runcomfy MCP?

Runcomfy MCP is distributed as a remote server. Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of runcomfy-com/runcomfy-mcp.

Is Runcomfy MCP free?

The code is published under the MIT licence and can be used free of charge.

Is Runcomfy MCP safe?

No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.

Is it an official server?

Yes: the awesome-mcp-servers list marks it as the service vendor's official implementation.

What are the alternatives to Runcomfy MCP?

In the same category: Pascal 3D Editor, Next AI Draw.io, Measure, and TerraVision. Pascal 3D Editor and Next AI Draw.io score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score