wait_any_completion · Claude Bridge MCP: Risk & Policy

WHAT IT DOES

What wait_any_completion does on Claude Bridge

AI agents invoke wait_any_completion to trigger actions in Claude Bridge. 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 wait_any_completion needs a policy

This tool appears to be part of a work-dispatch system that executes code in a devcontainer environment. 'wait_any_completion' likely blocks until any dispatched task completes, making it part of the execution pipeline.

From the tool's definition Tool name 'wait_any_completion' with empty description; belongs to server that 'dispatches work into Claude Code running inside your devcontainer over stdio'; sibling tools include 'dispatch', 'dispatch_async', and 'get_dispatch', suggesting this tool waits…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wait_any_completion Rate-limited

wait_any_completion 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": {
    "wait_any_completion": {
      "limits": [
        {
          "counter": "wait_any_completion_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 Claude Bridge, so you can run agents against it safely.

FAQ

Questions about wait_any_completion

What does the wait_any_completion tool do? +

wait_any_completion. It is categorised as a Execute tool in the Claude Bridge 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_any_completion? +

Register the Claude Bridge MCP server in PolicyLayer and add a rule for wait_any_completion: 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 Claude Bridge. Nothing to install.

What risk level is wait_any_completion? +

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

Can I rate-limit wait_any_completion? +

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

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

wait_any_completion is provided by the Claude Bridge MCP server (josiahsiegel/claude-bridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.