io.github.runcomfy-com/runcomfy-mcp

Official10 toolsLive

by runcomfy-com · Python

Remote MCP for RunComfy: ComfyUI deployments, hosted models, LoRA training. 31 tools.

io.github.runcomfy-com/runcomfy-mcp (Model Context Protocol Server)

This remote MCP server provides connectivity to the RunComfy Serverless API for ComfyUI. It is used to manage deployments, run inference, and retrieve results from AI assistants such as Claude, Cursor, and Windsurf, with support for serverless workflows.

🛠️ Key Features

Remote MCP server for RunComfy Serverless API (ComfyUI)
Manage deployments
Run inference and retrieve results
MCP endpoint: https://mcp.runcomfy.com/mcp
Docs available at https://docs.runcomfy.com/mcp

🚀 Use Cases

Deploy and update ComfyUI-based inference setups
Execute inference tasks and return results to AI assistants
Integrate image-generation and video-generation workflows via MCP

⚡ Developer Benefits

Compatible with Model Context Protocol (MCP)
Serverless API integration for ComfyUI
Tooling oriented toward async inference results retrieval

⚠️ Limitations

Designed specifically around RunComfy Serverless API (ComfyUI); not a general-purpose MCP for arbitrary backends

📌 Metadata

Topics: ai, comfyui, gpu, image-generation, mcp, mcp-server, model-context-protocol, runcomfy, serverless, video-generation
Tool count: 10

Topics

aicomfyuigpuimage-generationmcpmcp-servermodel-context-protocolruncomfyserverlessvideo-generation

Captured live from the server via tools/list.

list_deployments

List Serverless API deployments in the caller's account. Backs ``GET /prod/v2/deployments``. Args: ids: Optional list of deployment IDs to filter to. include_payload: Include workflow_api_json, overrides, and object_info_url for each deployment. Larger response. include_readme: Include the deployment's README markdown.

Parameters3

ids	any	optional
include_payload	boolean	optional
include_readme	boolean	optional

Raw schema

{
  "type": "object",
  "properties": {
    "ids": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Ids"
    },
    "include_payload": {
      "default": false,
      "title": "Include Payload",
      "type": "boolean"
    },
    "include_readme": {
      "default": false,
      "title": "Include Readme",
      "type": "boolean"
    }
  },
  "title": "list_deploymentsArguments"
}

get_deployment

Get one deployment by ID. Backs ``GET /prod/v2/deployments/{deployment_id}``. Set include_payload=true to inspect the deployed workflow graph (workflow_api_json) and default overrides — use the node IDs and input names to build the ``overrides`` for ``submit_request``.

Parameters3

deployment_id	string	required
include_payload	boolean	optional
include_readme	boolean	optional

Raw schema

{
  "type": "object",
  "properties": {
    "deployment_id": {
      "title": "Deployment Id",
      "type": "string"
    },
    "include_payload": {
      "default": false,
      "title": "Include Payload",
      "type": "boolean"
    },
    "include_readme": {
      "default": false,
      "title": "Include Readme",
      "type": "boolean"
    }
  },
  "required": [
    "deployment_id"
  ],
  "title": "get_deploymentArguments"
}

create_deployment

Create a Serverless API (ComfyUI) deployment. Backs ``POST /prod/v2/deployments``. For LoRA deployments, create via the runcomfy.com UI instead. Args: name: Human-readable name. workflow_id: UUID of the ComfyUI workflow. workflow_version: Version label, e.g. "v1". hardware: One of TURING_16, AMPERE_24, AMPERE_48, ADA_48_PLUS, AMPERE_80, ADA_80_PLUS, HOPPER_141. min_instances: 0..30. Warm instance floor (billable if > 0). max_instances: 1..60. Concurrency ceiling. queue_size: >= 0. Pending requests before scaling up. keep_warm_duration_in_seconds: >= 0. Idle timeout.

Parameters8

name	string	required
workflow_id	string	required
workflow_version	string	required
hardware	string	optional
min_instances	integer	optional
max_instances	integer	optional
queue_size	integer	optional
keep_warm_duration_in_seconds	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "title": "Name",
      "type": "string"
    },
    "workflow_id": {
      "title": "Workflow Id",
      "type": "string"
    },
    "workflow_version": {
      "title": "Workflow Version",
      "type": "string"
    },
    "hardware": {
      "default": "AMPERE_48",
      "title": "Hardware",
      "type": "string"
    },
    "min_instances": {
      "default": 0,
      "title": "Min Instances",
      "type": "integer"
    },
    "max_instances": {
      "default": 1,
      "title": "Max Instances",
      "type": "integer"
    },
    "queue_size": {
      "default": 1,
      "title": "Queue Size",
      "type": "integer"
    },
    "keep_warm_duration_in_seconds": {
      "default": 60,
      "title": "Keep Warm Duration In Seconds",
      "type": "integer"
    }
  },
  "required": [
    "name",
    "workflow_id",
    "workflow_version"
  ],
  "title": "create_deploymentArguments"
}

update_deployment

Partially update a deployment. Backs ``PATCH /prod/v2/deployments/{deployment_id}``. Only pass the fields you want to change. Set is_enabled=false to pause; true to re-enable.

Parameters9

deployment_id	string	required
name	any	optional
workflow_version	any	optional
hardware	any	optional
min_instances	any	optional
max_instances	any	optional
queue_size	any	optional
keep_warm_duration_in_seconds	any	optional
is_enabled	any	optional

Raw schema

{
  "type": "object",
  "properties": {
    "deployment_id": {
      "title": "Deployment Id",
      "type": "string"
    },
    "name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Name"
    },
    "workflow_version": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Workflow Version"
    },
    "hardware": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Hardware"
    },
    "min_instances": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Min Instances"
    },
    "max_instances": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Max Instances"
    },
    "queue_size": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Queue Size"
    },
    "keep_warm_duration_in_seconds": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Keep Warm Duration In Seconds"
    },
    "is_enabled": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Is Enabled"
    }
  },
  "required": [
    "deployment_id"
  ],
  "title": "update_deploymentArguments"
}

delete_deployment

Permanently delete a deployment. Backs ``DELETE /prod/v2/deployments/{deployment_id}``. This cannot be undone. Consider ``update_deployment(is_enabled=false)`` to pause instead.

Parameters1

deployment_id

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "deployment_id": {
      "title": "Deployment Id",
      "type": "string"
    }
  },
  "required": [
    "deployment_id"
  ],
  "title": "delete_deploymentArguments"
}

submit_request

Submit an async inference request to a deployment. Backs ``POST /prod/v1/deployments/{deployment_id}/inference``. Args: deployment_id: Target deployment. overrides: Partial graph keyed by node_id, e.g. ``{"6": {"inputs": {"text": "a cat"}}}``. Use ``get_deployment(include_payload=true)`` to discover node IDs and input names. workflow_api_json: Advanced — run a different workflow without updating the deployment. Omit ``overrides`` in this mode. extra_data: E.g. ``{"api_key_comfy_org": "comfyui-..."}`` for ComfyUI Core API nodes. webhook_url: Push-based updates instead of polling. webhook_intermediate_status: Fire webhooks on every status change, not just terminal. wait_for_completion: If true, poll until done and return the result inline. timeout_seconds: Max wait when wait_for_completion=true. File inputs: pass a public HTTPS URL or Base64 data URI directly in the overrides value, e.g. ``{"189": {"inputs": {"image": "https://example.com/photo.jpg"}}}`` or ``{"189": {"inputs": {"image": "data:image/jpeg;base64,/9j..."}}}``.

Parameters8

deployment_id	string	required
overrides	any	optional
workflow_api_json	any	optional
extra_data	any	optional
webhook_url	any	optional
webhook_intermediate_status	any	optional
wait_for_completion	boolean	optional
timeout_seconds	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "deployment_id": {
      "title": "Deployment Id",
      "type": "string"
    },
    "overrides": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Overrides"
    },
    "workflow_api_json": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Workflow Api Json"
    },
    "extra_data": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Extra Data"
    },
    "webhook_url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Webhook Url"
    },
    "webhook_intermediate_status": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Webhook Intermediate Status"
    },
    "wait_for_completion": {
      "default": false,
      "title": "Wait For Completion",
      "type": "boolean"
    },
    "timeout_seconds": {
      "default": 300,
      "title": "Timeout Seconds",
      "type": "integer"
    }
  },
  "required": [
    "deployment_id"
  ],
  "title": "submit_requestArguments"
}

get_request_status

Poll a request's current status. Backs ``GET /prod/v1/deployments/{deployment_id}/requests/{request_id}/status``. Lifecycle: ``in_queue`` → ``in_progress`` → ``completed`` / ``cancelled``.

Parameters2

deployment_id	string	required
request_id	string	required

Raw schema

{
  "type": "object",
  "properties": {
    "deployment_id": {
      "title": "Deployment Id",
      "type": "string"
    },
    "request_id": {
      "title": "Request Id",
      "type": "string"
    }
  },
  "required": [
    "deployment_id",
    "request_id"
  ],
  "title": "get_request_statusArguments"
}

get_request_result

Fetch a completed request's outputs. Backs ``GET /prod/v1/deployments/{deployment_id}/requests/{request_id}/result``. Output URLs are hosted for 7 days.

Parameters2

deployment_id	string	required
request_id	string	required

Raw schema

{
  "type": "object",
  "properties": {
    "deployment_id": {
      "title": "Deployment Id",
      "type": "string"
    },
    "request_id": {
      "title": "Request Id",
      "type": "string"
    }
  },
  "required": [
    "deployment_id",
    "request_id"
  ],
  "title": "get_request_resultArguments"
}

cancel_request

Cancel a queued or running request. Backs ``POST /prod/v1/deployments/{deployment_id}/requests/{request_id}/cancel``. Returns ``cancelled`` if accepted, ``not_cancellable`` if already done.

Parameters2

deployment_id	string	required
request_id	string	required

Raw schema

{
  "type": "object",
  "properties": {
    "deployment_id": {
      "title": "Deployment Id",
      "type": "string"
    },
    "request_id": {
      "title": "Request Id",
      "type": "string"
    }
  },
  "required": [
    "deployment_id",
    "request_id"
  ],
  "title": "cancel_requestArguments"
}

call_instance_proxy

Call a ComfyUI backend endpoint on a live instance. Backs ``POST /prod/v2/deployments/{deployment_id}/instances/{instance_id}/proxy/{path}``. Get the instance_id from ``get_request_status`` once the status is ``in_progress``. Common target: ``api/free`` with ``{"unload_models": true}`` to free GPU memory.

Parameters4

deployment_id	string	required
instance_id	string	required
comfy_backend_path	string	required
request_body	any	optional

Raw schema

{
  "type": "object",
  "properties": {
    "deployment_id": {
      "title": "Deployment Id",
      "type": "string"
    },
    "instance_id": {
      "title": "Instance Id",
      "type": "string"
    },
    "comfy_backend_path": {
      "title": "Comfy Backend Path",
      "type": "string"
    },
    "request_body": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Request Body"
    }
  },
  "required": [
    "deployment_id",
    "instance_id",
    "comfy_backend_path"
  ],
  "title": "call_instance_proxyArguments"
}

README.md14 KBView on GitHub

RunComfy MCP

MCP server for the RunComfy platform — Serverless API (ComfyUI), Model API, and Trainer API. Manage deployments, run hosted models, train LoRAs, and retrieve results from AI assistants like Claude, Cursor, and Windsurf.

Endpoint: https://mcp.runcomfy.com/mcp

Docs: docs.runcomfy.com/mcp

What it does

31 tools mirroring the RunComfy docs 1:1, across three products plus your account balance.

Serverless API (ComfyUI) — your own workflows on dedicated endpoints

Docs: docs.runcomfy.com/serverless

Category	Tools
Deployment management	`list_deployments`, `get_deployment`, `create_deployment`, `update_deployment`, `delete_deployment`
Inference	`submit_request`, `get_request_status`, `get_request_result`, `cancel_request`
Advanced	`call_instance_proxy`

Model API — hosted catalog models, on demand

Docs: docs.runcomfy.com/model-apis

Category	Tools
Catalog	`list_models`, `get_model`, `list_model_categories`
Inference	`run_model`, `get_model_request_status`, `get_model_request_result`, `cancel_model_request`

No deployment to manage and per-request billing. list_models browses the catalog by keyword or capability (category=image-to-video), get_model returns one model's input schema — property types, defaults, enums, and ranges — and run_model runs it. So an assistant can go from "make me a video" to a valid request without leaving the tools or guessing a parameter.

Entries also carry description, base_price_usd per price_unit, and a model_url to the model's page.

model_id is the identifier shown on the model's page at runcomfy.com/models, slashes included — e.g. blackforestlabs/flux-1-kontext/pro/edit. File inputs must be public HTTPS URLs.

Trainer API — datasets and AI Toolkit LoRA training

Docs: docs.runcomfy.com/trainer-apis

Category	Tools
Datasets	`create_dataset`, `list_datasets`, `get_dataset_status`, `delete_dataset`
Dataset uploads	`upload_dataset_file_from_url`, `upload_dataset_text_file`, `get_dataset_upload_urls`
Training jobs	`submit_training_job`, `get_training_job_status`, `get_training_job_result`, `cancel_training_job`, `resume_training_job`, `edit_training_job`

Typical flow: create a dataset → upload media and matching .txt captions → poll until READY → submit a job with an AI Toolkit YAML config → poll status → pull checkpoints from the result.

Because the server runs remotely it cannot read local files. Upload media it can reach over HTTP with upload_dataset_file_from_url, write captions inline with upload_dataset_text_file, and for local or >150 MB files use get_dataset_upload_urls and PUT the bytes to the signed URL yourself.

Account

Category	Tools
Balance	`get_balance`

One wallet funds all three products. get_balance reports what is left, in balance_usd for reading and balance_microdollars (millionths of a dollar) for exact threshold checks. It is served from api.runcomfy.net rather than mirrored per product, because there is only one figure to report.

Crossing between them

A trained LoRA runs without any deployment: pass its base model's model_id to run_model and the LoRA as an input, e.g. {"lora": {"path": "my_first_lora_3000.safetensors"}} — either a name from your LoRA Assets or a public URL such as a checkpoint from get_training_job_result. For a dedicated endpoint with chosen hardware, deploy it and use the Serverless tools instead.

Quick setup

Every client authenticates with a RunComfy API token from your Profile page. Two ways to supply it:

API token header — works in any Streamable HTTP client. Simplest, and the only option for clients without a browser OAuth flow.
Browser OAuth — no token in a config file. Supported by Claude.ai, Cursor, and local clients that register a loopback callback, such as Claude Code.

Claude Code

Token header (one command, nothing else to do):

bash

claude mcp add --transport http runcomfy https://mcp.runcomfy.com/mcp --header "Authorization: Bearer YOUR_RUNCOMFY_TOKEN"

Or browser OAuth — omit the header, then run /mcp inside Claude Code and pick Authenticate:

bash

claude mcp add --transport http runcomfy https://mcp.runcomfy.com/mcp

--transport http is the Streamable HTTP transport. streamable-http is not a value Claude Code accepts, and single-dash -transport / -header are not either — both forms fail before the server is ever contacted.

Check it with claude mcp list, which should show runcomfy: connected.

Claude.ai

Add https://mcp.runcomfy.com/mcp in Settings → Connectors → Add custom connector, then select Connect. Claude discovers RunComfy's OAuth 2.1 endpoints, opens a RunComfy consent page, and asks for one of the API tokens shown in your RunComfy Profile. The token is validated by RunComfy and encrypted inside the MCP authorization grant; it is never returned to Claude.

Cursor

.cursor/mcp.json:

json

{
  "mcpServers": {
    "runcomfy": {
      "url": "https://mcp.runcomfy.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_RUNCOMFY_TOKEN" }
    }
  }
}

VS Code (Copilot)

.vscode/mcp.json:

json

{
  "servers": {
    "runcomfy": {
      "type": "http",
      "url": "https://mcp.runcomfy.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_RUNCOMFY_TOKEN" }
    }
  }
}

Windsurf

Settings → MCP:

json

{
  "mcpServers": {
    "runcomfy": {
      "serverUrl": "https://mcp.runcomfy.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_RUNCOMFY_TOKEN" }
    }
  }
}

Any other client

URL: https://mcp.runcomfy.com/mcp
Transport: Streamable HTTP
Auth: Authorization: Bearer <token> on every request, or OAuth 2.1 with a loopback redirect URI or an exact supported client callback

Troubleshooting

Symptom	Cause
`401` with `RunComfy rejected this API token`	The token is wrong, expired, or truncated on copy. Generate a new one in Profile — the response body names the fix.
`401` with no `error_description`	No `Authorization` header reached the server. Check the header is quoted as one argument: `--header "Authorization: Bearer ..."`.
`invalid_client_metadata` during OAuth	The client registered a callback outside the loopback and exact client allowlist. Use a supported callback or the token header.
`invalid_target` during OAuth	The configured URL must be exactly `https://mcp.runcomfy.com/mcp` — no trailing slash. RFC 8707 binds the token to that exact resource.
`503` with `Retry-After`	RunComfy's API could not be reached to verify the token. Retry.
`429`	More than 600 token-authenticated requests a minute from one IP.

Revoke access by regenerating the token in your RunComfy Profile. That invalidates the token header and any OAuth grant built on it, because every MCP request revalidates the token upstream.

Architecture

code

MCP Client ──RunComfy API token──┐
                                 │   Cloudflare Worker (/mcp)
MCP Client ──MCP OAuth token─────┤   validates the credential, resolves
                                 │   it to one user's RunComfy token
                                 ▼
                         Cloudflare Container
                         (Python FastMCP app)
                                 │ request-scoped RunComfy credential
                 ┌───────────────┼───────────────┐
                 ▼               ▼               ▼
        api.runcomfy.net  model-api.       trainer-api.
         (Serverless)     runcomfy.net     runcomfy.net
                            (Model)          (Trainer)

One RunComfy token authenticates all three products, so the same credential resolution covers every tool.

Both credential kinds converge on the same request-scoped identity header before the container is reached. They are told apart by shape: OAuth access tokens are always userId:grantId:secret, and a RunComfy API token never contains a colon.

Cloudflare Worker (src/index.ts) — OAuth 2.1 authorization server and protected-resource boundary. Missing, invalid, expired, or wrong-audience credentials are rejected before MCP initialization or tool discovery.
Direct API token (src/index.ts) — a RunComfy Profile token presented as Authorization: Bearer is revalidated against api.runcomfy.net on every request, rate-limited per source IP, and never forwarded as-is.
OAuth consent (src/oauth-bridge.ts) — validates an existing RunComfy Profile token, stores it only in encrypted OAuth grant data, and issues a separate audience-bound MCP access token. Dynamic client registration accepts loopback callbacks (Claude Code and other local clients), an exact allowlist of hosted client callbacks, and Cursor's exact legacy app callback. Cursor registers cursor://anysphere.cursor-mcp/oauth/callback, https://www.cursor.com/agents/mcp/oauth/callback, and http://localhost:8787/callback together; all three must be accepted even when the active redirect uses localhost. Arbitrary custom protocols and callback variants remain rejected, and S256 PKCE is required.
Python container (server.py) — FastMCP app with 31 tools across the Serverless, Model, and Trainer APIs. It has no shared/operator credential and fails closed unless the authenticated edge supplies the current user's request-scoped RunComfy token.
Cloudflare Container auto-starts on first request, sleeps after 10 minutes idle.

Project layout

code

.github/workflows/deploy.yml  CI: typecheck, test, deploy to Cloudflare
src/index.ts          Cloudflare Worker entrypoint
src/oauth-bridge.ts   OAuth consent and RunComfy token validation
server.py             MCP tool definitions (31 tools)
runcomfy_client.py    RunComfy API clients (serverless, model, trainer)
container_app.py      ASGI middleware (request IDs, token forwarding)
container_entrypoint.py  Uvicorn startup
container_runtime.py  Env validation, structured logging
wrangler.jsonc        Cloudflare Worker + Container config
Dockerfile            Container image
.env.example          Local dev config

Local development

bash

# Python 3.11+
python3.11 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env
python -m container_entrypoint

Local endpoints:

http://127.0.0.1:8000/healthz
http://127.0.0.1:8000/mcp

The local Python endpoint intentionally has no shared fallback credential. Protected tool calls must go through the authenticated Worker boundary.

Deploy

Pushing to main deploys automatically via .github/workflows/deploy.yml: typecheck, Worker tests, and container tests must pass, then wrangler deploy --containers-rollout immediate ships the Worker and the Python container together. Pull requests run the same checks without deploying. The workflow can also be run by hand from the Actions tab.

One repository secret is required:

Secret	Purpose
`CLOUDFLARE_API_TOKEN`	A token with Edit Cloudflare Workers permission on the account in `wrangler.jsonc`
`CLOUDFLARE_ACCOUNT_ID`	Optional. `account_id` is already committed in `wrangler.jsonc`; set this only to deploy under a different account.

To deploy by hand (requires Cloudflare Workers Paid plan with Containers enabled):

bash

npm install
npm run check
npm test
npx wrangler deploy --containers-rollout immediate

The MCP endpoint goes live at https://mcp.runcomfy.com/mcp (custom domain configured in wrangler.jsonc).

Environment variables and bindings

There is deliberately no shared RunComfy API-key secret. OAuth state is kept in the OAUTH_KV binding and every upstream request is tied to the user who authorized the OAuth grant.

Worker vars (in `wrangler.jsonc`)

Name	Default	Description
`CONTAINER_INSTANCE_NAME`	`runcomfy-unified`	Durable Object instance name
`CONTAINER_STARTUP_TIMEOUT_MS`	`15000`	Max wait for container start
`CONTAINER_PORT_READY_TIMEOUT_MS`	`30000`	Max wait for port ready
`MCP_MAX_BODY_BYTES`	`1048576`	Max request body size
`OPENAI_APPS_CHALLENGE`	Current submission token	Public OpenAI domain-verification token, served verbatim at `GET /.well-known/openai-apps-challenge`; unset or empty returns 404. Verify ownership of any existing token before replacing it.
`MCP_DIRECT_TOKEN_RATE_LIMITER`	600 / 60s	Per-IP cap on API-token-authenticated `/mcp` requests
`RUNCOMFY_SERVERLESS_BASE_URL`	`https://api.runcomfy.net`	Serverless API base URL
`RUNCOMFY_MODEL_API_BASE_URL`	`https://model-api.runcomfy.net`	Model API base URL
`RUNCOMFY_TRAINER_API_BASE_URL`	`https://trainer-api.runcomfy.net`	Trainer API base URL

Local Python dev (`.env` file)

Name	Required	Description
`RUNCOMFY_SERVERLESS_BASE_URL`	No	Override Serverless base URL (default: `https://api.runcomfy.net`)
`RUNCOMFY_MODEL_API_BASE_URL`	No	Override Model API base URL (default: `https://model-api.runcomfy.net`)
`RUNCOMFY_TRAINER_API_BASE_URL`	No	Override Trainer API base URL (default: `https://trainer-api.runcomfy.net`)
`RUNCOMFY_MCP_MOUNT_PREFIX`	No	Path prefix for MCP mount (default: empty)

Install

Tools (10)

list_deploymentsget_deploymentcreate_deploymentupdate_deploymentdelete_deploymentsubmit_requestget_request_statusget_request_result

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.runcomfy.com/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "runcomfy-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.runcomfy.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.runcomfy-com/runcomfy-mcp (Model Context Protocol Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

📌 Metadata

Topics

list_deployments

get_deployment

create_deployment

update_deployment

delete_deployment

submit_request

get_request_status

get_request_result

cancel_request

call_instance_proxy

RunComfy MCP

What it does

Serverless API (ComfyUI) — your own workflows on dedicated endpoints

Model API — hosted catalog models, on demand

Trainer API — datasets and AI Toolkit LoRA training

Account

Crossing between them

Quick setup

Claude Code

Claude.ai

Cursor

VS Code (Copilot)

Windsurf

Any other client

Troubleshooting

Architecture

Project layout

Local development

Deploy

Environment variables and bindings

Worker vars (in wrangler.jsonc)

Local Python dev (.env file)

Install

Remote endpoint

Related servers

Worker vars (in `wrangler.jsonc`)

Local Python dev (`.env` file)