gsd_run · Gsd MCP: Risk & Policy

WHAT IT DOES

What gsd_run does on Gsd

AI agents invoke gsd_run to trigger actions in Gsd. 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 gsd_run needs a policy

This tool allows execution of arbitrary GSD commands without apparent restriction. While the actual impact depends on what GSD commands can do, the unrestricted 'any' qualifier and the 'Run' verb place this firmly in the Execute category. The high severity reflects that an AI agent given this tool could trigger unintended operations across the GSD lifecycle (phases, milestones, commits, deployments, etc.).

From the tool's definition Tool description states 'Run any GSD command directly' - the word 'Run' combined with 'any' GSD command indicates arbitrary command execution with broad scope.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gsd_run Rate-limited

gsd_run 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": {
    "gsd_run": {
      "limits": [
        {
          "counter": "gsd_run_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 Gsd, so you can run agents against it safely.

FAQ

Questions about gsd_run

What does the gsd_run tool do? +

Run any GSD command directly (see gsd://help for full list). It is categorised as a Execute tool in the Gsd MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on gsd_run? +

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

What risk level is gsd_run? +

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

Can I rate-limit gsd_run? +

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

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

gsd_run is provided by the Gsd MCP server (m0-ar/gsd-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.