bruno_run_request · Bruno MCP Server MCP: Risk & Policy

WHAT IT DOES

What bruno_run_request does on Bruno MCP Server

AI agents invoke bruno_run_request to trigger actions in Bruno 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 bruno_run_request needs a policy

This tool executes arbitrary API requests from a collection, which can trigger external operations and side effects. While the request definitions themselves are pre-configured in the collection, an AI agent could be manipulated into running requests that modify remote systems (via POST/PUT/DELETE), call external services, or trigger unintended state changes.

From the tool's definition Tool description states 'Run a specific request from a Bruno collection'. The verb 'Run' and the context of executing API requests indicates code/operation execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

bruno_run_request Rate-limited

bruno_run_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": {
    "bruno_run_request": {
      "limits": [
        {
          "counter": "bruno_run_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 Bruno MCP Server, so you can run agents against it safely.

FAQ

Questions about bruno_run_request

What does the bruno_run_request tool do? +

Run a specific request from a Bruno collection. It is categorised as a Execute tool in the Bruno 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 bruno_run_request? +

Register the Bruno MCP Server MCP server in PolicyLayer and add a rule for bruno_run_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 Bruno MCP Server. Nothing to install.

What risk level is bruno_run_request? +

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

Can I rate-limit bruno_run_request? +

Yes. Add a rate_limit block to the bruno_run_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 bruno_run_request completely? +

Set action: deny in the PolicyLayer policy for bruno_run_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 bruno_run_request? +

bruno_run_request is provided by the Bruno MCP Server MCP server (jcr82/bruno-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.