timeout · Malicious MCP: Risk & Policy

WHAT IT DOES

What timeout does on Malicious

AI agents invoke timeout to trigger actions in Malicious. 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.

PARAMETERS

Parameter	Type	Required	Description
`seconds`	string	—	Number of seconds to wait

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why timeout needs a policy

This tool triggers a timed blocking operation on the server side. In a malicious context, it can be used for denial-of-service by tying up resources, causing timeouts in dependent systems, or as a stalling mechanism within agent workflows. The malicious server label elevates concern. Classified as Execute because it actively runs a wait/blocking operation whose effect depends on the argument supplied.

From the tool's definition 'Waits for specified number of seconds before responding' — deliberately induces delay/blocking behavior; server is explicitly labeled 'deliberately malicious MCP server for E2E testing purposes'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

timeout Rate-limited

timeout 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": {
    "timeout": {
      "limits": [
        {
          "counter": "timeout_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 Malicious, so you can run agents against it safely.

FAQ

Questions about timeout

What does the timeout tool do? +

Waits for specified number of seconds before responding. It is categorised as a Execute tool in the Malicious MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does timeout accept? +

timeout accepts 1 parameter: seconds. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on timeout? +

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

What risk level is timeout? +

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

Can I rate-limit timeout? +

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

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

timeout is provided by the Malicious MCP server (malicious-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.