send_request · Req MCP: Risk & Policy

WHAT IT DOES

What send_request does on Req

AI agents invoke send_request to trigger actions in Req. 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 send_request needs a policy

This tool executes arbitrary HTTP requests against external endpoints. It supports session-aware operations including cookie persistence and bearer token reuse, meaning a misused invocation could trigger state-changing operations (POST, PUT, DELETE) on real APIs with authenticated sessions.

From the tool's definition "Sends an HTTP request using the current Request API session"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_request Rate-limited

send_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": {
    "send_request": {
      "limits": [
        {
          "counter": "send_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 Req, so you can run agents against it safely.

FAQ

Questions about send_request

What does the send_request tool do? +

Sends an HTTP request using the current Request API session. It is categorised as a Execute tool in the Req MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_request? +

Register the Req MCP server in PolicyLayer and add a rule for send_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 Req. Nothing to install.

What risk level is send_request? +

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

Can I rate-limit send_request? +

Yes. Add a rate_limit block to the send_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 send_request completely? +

Set action: deny in the PolicyLayer policy for send_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 send_request? +

send_request is provided by the Req MCP server (tarminarx/request-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.