High Risk →

wait-task

Block until a task settles or asks for input. Returns as soon as the task reaches a terminal state (`completed`, `failed`, `cancelled`) or enters `input_required`. If `timeout_ms` elapses first, it returns the current status. PATTERN: loop `wait-task` → if `input_required`, call `respond-task` ...

Part of the Mcp Codex Worker MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

mcp-codex-worker Execute Risk 3/5

AI agents invoke wait-task to trigger processes or run actions in Mcp Codex Worker. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.

wait-task can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. Intercept enforces rate limits and validates arguments to keep execution within safe bounds.

Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.

mcp-codex-worker.yaml
tools:
  wait-task:
    rules:
      - action: allow
        rate_limit:
          max: 10
          window: 60
        validate:
          required_args: true

See the full Mcp Codex Worker policy for all 5 tools.

Tool Name wait-task
Category Execute
Risk Level High

Agents calling execute-class tools like wait-task have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Execute risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

wait-task is one of the high-risk operations in Mcp Codex Worker. For the full severity-focused view — only the high-risk tools with their recommended policies — see the breakdown for this server, or browse all high-risk tools across every MCP server.

What does the wait-task tool do? +

Block until a task settles or asks for input. Returns as soon as the task reaches a terminal state (`completed`, `failed`, `cancelled`) or enters `input_required`. If `timeout_ms` elapses first, it returns the current status. PATTERN: loop `wait-task` → if `input_required`, call `respond-task` → loop back. Give each call enough time to catch meaningful progress.. It is categorised as a Execute tool in the Mcp Codex Worker MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on wait-task? +

Add a rule in your Intercept YAML policy under the tools section for wait-task. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Mcp Codex Worker MCP server.

What risk level is wait-task? +

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

Can I rate-limit wait-task? +

Yes. Add a rate_limit block to the wait-task rule in your Intercept 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 wait-task completely? +

Set action: deny in the Intercept policy for wait-task. 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 wait-task? +

wait-task is provided by the Mcp Codex Worker MCP server (mcp-codex-worker). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Mcp Codex Worker

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.