put_request · API Tester MCP Server MCP: Risk & Policy

WHAT IT DOES

What put_request does on API Tester MCP Server

AI agents use put_request to create or update resources in API Tester MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your API Tester MCP Server environment.

WHY IT NEEDS A POLICY

Why put_request needs a policy

PUT requests create or replace resources at a specified URL. This is a Write operation as it modifies or overwrites data. Severity is high because the tool can make arbitrary PUT requests to any URL on behalf of the user, potentially modifying or replacing data on any accessible API endpoint, with broad blast radius depending on the target URL.

From the tool's definition Make a PUT request with a JSON body to the specified URL

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

put_request Rate-limited

put_request stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "put_request": {
      "limits": [
        {
          "counter": "put_request_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches API Tester MCP Server, so you can run agents against it safely.

FAQ

Questions about put_request

What does the put_request tool do? +

Make a PUT request with a JSON body to the specified URL. It is categorised as a Write tool in the API Tester MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on put_request? +

Register the API Tester MCP Server MCP server in PolicyLayer and add a rule for put_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 API Tester MCP Server. Nothing to install.

What risk level is put_request? +

put_request is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit put_request? +

Yes. Add a rate_limit block to the put_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 put_request completely? +

Set action: deny in the PolicyLayer policy for put_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 put_request? +

put_request is provided by the API Tester MCP Server MCP server (vikrant-khedkar/api-tester-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.