rerun · RespCode MCP Server MCP: Risk & Policy

WHAT IT DOES

What rerun does on RespCode MCP Server

AI agents invoke rerun to trigger actions in RespCode MCP Server. 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 rerun needs a policy

The 'rerun' tool triggers execution of previously generated code on different hardware architectures (x86_64, ARM, RISC-V). This is an Execute operation because it runs code whose effects depend on the architecture and the code being re-executed. While not inherently destructive, it has a high blast radius if an agent re-executes malicious or resource-intensive code without authorization.

From the tool's definition Tool description states 're-run a previous prompt on a different architecture' which involves executing code.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rerun Rate-limited

rerun 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": {
    "rerun": {
      "limits": [
        {
          "counter": "rerun_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 RespCode MCP Server, so you can run agents against it safely.

FAQ

Questions about rerun

What does the rerun tool do? +

Re-run a previous prompt on a different architecture. It is categorised as a Execute tool in the RespCode MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on rerun? +

Register the RespCode MCP Server MCP server in PolicyLayer and add a rule for rerun: 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 RespCode MCP Server. Nothing to install.

What risk level is rerun? +

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

Can I rate-limit rerun? +

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

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

rerun is provided by the RespCode MCP Server MCP server (respcodeai/respcode-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.