obsidian_launch_app · Mcp Apple Obsidian MCP: Risk & Policy

WHAT IT DOES

What obsidian_launch_app does on Mcp Apple Obsidian

AI agents invoke obsidian_launch_app to trigger actions in Mcp Apple Obsidian. 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 obsidian_launch_app needs a policy

Launching an application is an Execute action: it runs an external process/operation outside the model's environment. While the blast radius is low (Obsidian is a local note-taking app, not a destructive or financial operation), it remains in the Execute category because it performs a triggered action on the system. The optional vault parameter makes the outcome dependent on supplied arguments.

From the tool's definition Tool description states 'Launch the Obsidian application, optionally opening a specific vault' — this triggers an external application launch, which is an operation whose effects depend on the argument (which vault to open).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

obsidian_launch_app Rate-limited

obsidian_launch_app 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": {
    "obsidian_launch_app": {
      "limits": [
        {
          "counter": "obsidian_launch_app_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 Mcp Apple Obsidian, so you can run agents against it safely.

FAQ

Questions about obsidian_launch_app

What does the obsidian_launch_app tool do? +

Launch the Obsidian application, optionally opening a specific vault. It is categorised as a Execute tool in the Mcp Apple Obsidian MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on obsidian_launch_app? +

Register the Mcp Apple Obsidian MCP server in PolicyLayer and add a rule for obsidian_launch_app: 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 Mcp Apple Obsidian. Nothing to install.

What risk level is obsidian_launch_app? +

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

Can I rate-limit obsidian_launch_app? +

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

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

obsidian_launch_app is provided by the Mcp Apple Obsidian MCP server (rex/mcp-apple-obsidian). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.