call · MCP Gateway MCP: Risk & Policy

WHAT IT DOES

What call does on MCP Gateway

AI agents invoke call 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 call needs a policy

This is a meta-tool that can invoke any tool registered behind the gateway, meaning its effective category and severity span the full range (Read through Financial/Destructive) depending on the downstream tool invoked. Since it can execute arbitrary tool calls — including destructive, financial, or code-executing ones — the worst-case blast radius is critical.

From the tool's definition "Call a tool through the gateway" — this tool proxies arbitrary tool calls to downstream MCP servers, with the actual effect determined entirely by which tool and arguments are passed.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

call Rate-limited

call 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": {
      "limits": [
        {
          "counter": "call_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 call

What does the call tool do? +

Call a tool through the gateway (with auth, policy, audit, metering). 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 call? +

Register the MCP Gateway MCP server in PolicyLayer and add a rule for call: 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 call? +

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

Can I rate-limit call? +

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

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

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