run_templates
AI agents invoke run_templates to trigger actions in ComfyUI-APP-MCP. 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 triggers execution of ComfyUI workflows, which are external operations that generate multimedia content. While the description is empty, the name combined with the server's stated purpose and sibling context (run_template, ComfyUI invocation) clearly indicates code/workflow execution rather than simple data retrieval.
From the tool's definition Tool name is 'run_templates' (plural); sibling tools include 'run_template' which invokes ComfyUI workflows for multimedia generation.
Attacks that exploit this kind of access
run_templates. It is categorised as a Execute tool in the ComfyUI-APP-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ComfyUI-APP- MCP server in PolicyLayer and add a rule for run_templates: 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-APP-MCP. Nothing to install.
run_templates 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_templates 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_templates. 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_templates is provided by the ComfyUI-APP- MCP server (luo-lotus/comfyui-app-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →