open_in_darktable · Darktable MCP: Risk & Policy

WHAT IT DOES

What open_in_darktable does on Darktable

AI agents invoke open_in_darktable to trigger actions in Darktable. 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 open_in_darktable needs a policy

This tool launches an external GUI application (darktable), which constitutes triggering an external operation. It is not purely reading data, nor writing/modifying files directly, but rather executing an external process. The description is incomplete ('The folder is' is truncated), which lowers confidence slightly, but the 'Launch' keyword clearly indicates execution of an external program.

From the tool's definition 'Launch the darktable GUI on a folder' — triggers an external application (darktable GUI) to open

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

open_in_darktable Rate-limited

open_in_darktable 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": {
    "open_in_darktable": {
      "limits": [
        {
          "counter": "open_in_darktable_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 Darktable, so you can run agents against it safely.

FAQ

Questions about open_in_darktable

What does the open_in_darktable tool do? +

Launch the darktable GUI on a folder. The folder is. It is categorised as a Execute tool in the Darktable MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on open_in_darktable? +

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

What risk level is open_in_darktable? +

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

Can I rate-limit open_in_darktable? +

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

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

open_in_darktable is provided by the Darktable MCP server (w1ne/darktable-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.