AI agents invoke run_workflow_from_file to trigger actions in ComfyUI MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool runs a workflow from a file, which constitutes executing code/commands in an external system (ComfyUI). While not immediately destructive or financial, it can consume computational resources, generate arbitrary content, and potentially interact with system resources depending on the workflow definition. The severity is high because an AI agent could be tricked into running malicious workflows.
From the tool's definition Tool executes a workflow from a file, which triggers external operations (image generation) whose effects depend on the file contents and ComfyUI configuration. The description states 'Run a workflow from a file' - a direct execution verb.
Documented attack patterns abuse exactly the kind of access run_workflow_from_file gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ComfyUI MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_workflow_from_file:
{
"version": "1",
"default": "deny",
"tools": {
"run_workflow_from_file": {
"limits": [
{
"counter": "run_workflow_from_file_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_workflow_from_file stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run a workflow from a file. It is categorised as a Execute tool in the ComfyUI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ComfyUI MCP Server MCP server in PolicyLayer and add a rule for run_workflow_from_file: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches ComfyUI MCP Server. Nothing to install.
run_workflow_from_file is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_workflow_from_file rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for run_workflow_from_file. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
run_workflow_from_file is provided by the ComfyUI MCP Server MCP server (overseer66/comfyui-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ComfyUI MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 ComfyUI MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.