sendRequest · gRPC MCP Server MCP: Risk & Policy

WHAT IT DOES

What sendRequest does on gRPC MCP Server

AI agents invoke sendRequest to trigger actions in gRPC 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 sendRequest needs a policy

Sending arbitrary gRPC requests to external servers is an Execute-class action. The actual impact depends on what RPC method is invoked — it could read data, write data, or trigger destructive operations on the remote server. Since the tool supports arbitrary unary RPCs, the worst-case misuse is high: an AI agent could call any available gRPC method, including ones that mutate or delete data on remote systems.

From the tool's definition 'Send a request to a gRPC server' — this tool triggers external operations by sending gRPC calls to remote servers, with effects entirely dependent on the arguments (endpoint, method, payload).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sendRequest Rate-limited

sendRequest 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": {
    "sendRequest": {
      "limits": [
        {
          "counter": "sendrequest_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 gRPC MCP Server, so you can run agents against it safely.

FAQ

Questions about sendRequest

What does the sendRequest tool do? +

Send a request to a gRPC server. It is categorised as a Execute tool in the gRPC 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 sendRequest? +

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

What risk level is sendRequest? +

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

Can I rate-limit sendRequest? +

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

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

sendRequest is provided by the gRPC MCP Server MCP server (yuki4-dev/grpc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.