replay_request · Hookray MCP: Risk & Policy

WHAT IT DOES

What replay_request does on Hookray

AI agents invoke replay_request to trigger actions in Hookray. 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 replay_request needs a policy

This tool actively sends HTTP requests to arbitrary destinations reachable from the host machine. It triggers external network operations whose effects depend on the destination and payload — e.g., replaying a POST to a payment endpoint, a write API, or an internal service.

From the tool's definition 'Replay a captured HookRay request to any destination reachable from this machine'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

replay_request Rate-limited

replay_request 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": {
    "replay_request": {
      "limits": [
        {
          "counter": "replay_request_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 Hookray, so you can run agents against it safely.

FAQ

Questions about replay_request

What does the replay_request tool do? +

Replay a captured HookRay request to any destination reachable from this machine. It is categorised as a Execute tool in the Hookray MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on replay_request? +

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

What risk level is replay_request? +

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

Can I rate-limit replay_request? +

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

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

replay_request is provided by the Hookray MCP server (shotatanikawa/hookray-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

replay_request is one line of Hookray's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →