entire_resume · Entire MCP: Risk & Policy

WHAT IT DOES

What entire_resume does on Entire

AI agents invoke entire_resume to trigger actions in Entire. 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 entire_resume needs a policy

This tool performs multiple active operations: checking out a branch (a git operation that modifies the working state), restoring session metadata (writes state), and returning a command to continue an agent session (triggers external operations). These combined actions go beyond a simple read, involving state changes and branch manipulation.

From the tool's definition "Check out a branch, restore session metadata, and get the command to continue an AI agent session"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

entire_resume Rate-limited

entire_resume 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": {
    "entire_resume": {
      "limits": [
        {
          "counter": "entire_resume_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 Entire, so you can run agents against it safely.

FAQ

Questions about entire_resume

What does the entire_resume tool do? +

Check out a branch, restore session metadata, and get the command to continue an AI agent session. Uses \. It is categorised as a Execute tool in the Entire MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on entire_resume? +

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

What risk level is entire_resume? +

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

Can I rate-limit entire_resume? +

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

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

entire_resume is provided by the Entire MCP server (jurislm/entire-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.