gateway_call_tool · MCP Gateway MCP: Risk & Policy

WHAT IT DOES

What gateway_call_tool does on MCP Gateway

AI agents invoke gateway_call_tool to trigger actions in MCP Gateway. 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 gateway_call_tool needs a policy

This is a meta-tool that executes arbitrary tools on backend servers. Its blast radius is critical because it can trigger any operation (Read, Write, Execute, Destructive, Financial) depending on what tool is called on which backend server.

From the tool's definition 'Call a tool on a backend MCP server' — this tool acts as a proxy executor that can invoke any tool on any backend MCP server, with auto-connection on demand.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gateway_call_tool Rate-limited

gateway_call_tool 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": {
    "gateway_call_tool": {
      "limits": [
        {
          "counter": "gateway_call_tool_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 Gateway, so you can run agents against it safely.

FAQ

Questions about gateway_call_tool

What does the gateway_call_tool tool do? +

Call a tool on a backend MCP server. The server will be auto-connected if not already loaded. It is categorised as a Execute tool in the MCP Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on gateway_call_tool? +

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

What risk level is gateway_call_tool? +

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

Can I rate-limit gateway_call_tool? +

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

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

gateway_call_tool is provided by the MCP Gateway MCP server (raiansar/mcp-gateway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.