call_api_raw · MCP: Risk & Policy

WHAT IT DOES

What call_api_raw does on Mcp

AI agents invoke call_api_raw to trigger actions in Mcp. 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 call_api_raw needs a policy

This tool executes arbitrary HTTP requests with full control over method (including POST, PUT, DELETE, PATCH), URL, headers, and body. Depending on the arguments supplied, it could perform reads, writes, deletions, or financial operations. Because the outcome depends entirely on the arguments and spans all categories, Execute is appropriate as it triggers external operations with variable effects.

From the tool's definition Make a raw HTTP request with full control over method, URL construction, headers, query params, body mode, and response parsing.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

call_api_raw Rate-limited

call_api_raw 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": {
    "call_api_raw": {
      "limits": [
        {
          "counter": "call_api_raw_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 Mcp, so you can run agents against it safely.

FAQ

Questions about call_api_raw

What does the call_api_raw tool do? +

Make a raw HTTP request with full control over method, URL construction, headers, query params, body mode, and response parsing. It is categorised as a Execute tool in the Mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on call_api_raw? +

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

What risk level is call_api_raw? +

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

Can I rate-limit call_api_raw? +

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

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

call_api_raw is provided by the MCP server (victormyschik/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.