run_and_summarize · Unlimited MCP: Risk & Policy

WHAT IT DOES

What run_and_summarize does on Unlimited

AI agents invoke run_and_summarize to trigger actions in Unlimited. 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_and_summarize needs a policy

The tool executes work delegated to background agents ('coding and sysops work'), which are forms of code execution and system operations. This has side effects dependent on the work items submitted and could harm systems or data if misused.

From the tool's definition Tool name 'run_and_summarize' indicates execution of code/commands. Server description confirms it 'delegates coding and sysops work' and uses 'git worktree isolation' and 'safety policies' — suggesting the tool runs arbitrary operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_and_summarize Rate-limited

run_and_summarize 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_and_summarize": {
      "limits": [
        {
          "counter": "run_and_summarize_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 Unlimited, so you can run agents against it safely.

FAQ

Questions about run_and_summarize

What does the run_and_summarize tool do? +

run_and_summarize. It is categorised as a Execute tool in the Unlimited 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_and_summarize? +

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

What risk level is run_and_summarize? +

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

Can I rate-limit run_and_summarize? +

Yes. Add a rate_limit block to the run_and_summarize 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_and_summarize completely? +

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

run_and_summarize is provided by the Unlimited MCP server (triumsebas/unlimited-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.