run_mermaid_cli · Diagram MCP: Risk & Policy

WHAT IT DOES

What run_mermaid_cli does on DiagramMCP

AI agents invoke run_mermaid_cli to trigger actions in DiagramMCP. 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.

WHY IT NEEDS A POLICY

Why run_mermaid_cli needs a policy

This tool executes external CLI commands (Mermaid) which could be weaponized for arbitrary code execution or resource exhaustion if an AI agent can inject malicious arguments. While the intended use case is diagram generation, the ability to 'run' a CLI creates Execute-level risk.

From the tool's definition Tool name 'run_mermaid_cli' indicates execution of Mermaid CLI commands. Server description states it 'generates various software development diagrams' and 'provides instructions for exporting results to multiple formats including SVG and PNG', confirming…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_mermaid_cli Rate-limited

run_mermaid_cli 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_mermaid_cli": {
      "limits": [
        {
          "counter": "run_mermaid_cli_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches DiagramMCP, so you can run agents against it safely.

FAQ

Questions about run_mermaid_cli

What does the run_mermaid_cli tool do? +

run_mermaid_cli. It is categorised as a Execute tool in the DiagramMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_mermaid_cli? +

Register the Diagram MCP server in PolicyLayer and add a rule for run_mermaid_cli: 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 DiagramMCP. Nothing to install.

What risk level is run_mermaid_cli? +

run_mermaid_cli is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_mermaid_cli? +

Yes. Add a rate_limit block to the run_mermaid_cli 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.

How do I block run_mermaid_cli completely? +

Set action: deny in the PolicyLayer policy for run_mermaid_cli. 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.

What MCP server provides run_mermaid_cli? +

run_mermaid_cli is provided by the Diagram MCP server (lelondelonmelon/diagrammcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.