invoke_function · Run402 MCP: Risk & Policy

WHAT IT DOES

What invoke_function does on Run402

AI agents invoke invoke_function to trigger actions in Run402. 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 invoke_function needs a policy

This tool triggers execution of deployed functions with effects dependent on arguments. While not inherently destructive or financial, the ability to invoke arbitrary deployed functions in an autonomous coding infrastructure creates high blast radius for misuse (could invoke functions that modify data, call external APIs, or perform unintended operations).

From the tool's definition Tool name 'invoke_function' combined with description 'Invoke a deployed function via HTTP' indicates execution of arbitrary deployed code.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

invoke_function Rate-limited

invoke_function 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": {
    "invoke_function": {
      "limits": [
        {
          "counter": "invoke_function_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 Run402, so you can run agents against it safely.

FAQ

Questions about invoke_function

What does the invoke_function tool do? +

Invoke a deployed function via HTTP. Returns the function. It is categorised as a Execute tool in the Run402 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on invoke_function? +

Register the Run402 MCP server in PolicyLayer and add a rule for invoke_function: 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 Run402. Nothing to install.

What risk level is invoke_function? +

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

Can I rate-limit invoke_function? +

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

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

invoke_function is provided by the Run402 MCP server (kychee-com/run402). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.