command_execute · Connect MCP: Risk & Policy

WHAT IT DOES

What command_execute does on Connect MCP

AI agents invoke command_execute to trigger actions in Connect 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.

WHY IT NEEDS A POLICY

Why command_execute needs a policy

This tool allows execution of arbitrary Obsidian commands and plugin actions, whose effects depend entirely on which command ID is supplied by the AI agent. While the blast radius is constrained to the Obsidian vault environment (not system-wide code execution), it still qualifies as Execute rather than Write because: (1) it explicitly executes commands, (2) effects are unpredictable and depend on runtime arguments,…

From the tool's definition Tool description explicitly states "Execute an Obsidian command by its ID" and "can run Templater templates, MetaBind actions, and any other plugin commands." The word "Execute" combined with the ability to run arbitrary plugin commands indicates code/command…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

command_execute Rate-limited

command_execute 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": {
    "command_execute": {
      "limits": [
        {
          "counter": "command_execute_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 Connect MCP, so you can run agents against it safely.

FAQ

Questions about command_execute

What does the command_execute tool do? +

Execute an Obsidian command by its ID. Use command_list to discover available commands. This can run Templater templates, MetaBind actions, and any other plugin commands. It is categorised as a Execute tool in the Connect MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on command_execute? +

Register the Connect MCP server in PolicyLayer and add a rule for command_execute: 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 Connect MCP. Nothing to install.

What risk level is command_execute? +

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

Can I rate-limit command_execute? +

Yes. Add a rate_limit block to the command_execute 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 command_execute completely? +

Set action: deny in the PolicyLayer policy for command_execute. 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 command_execute? +

command_execute is provided by the Connect MCP server (joch/obsidian-connect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.