dispatch_async · Claude Bridge MCP: Risk & Policy

WHAT IT DOES

What dispatch_async does on Claude Bridge

AI agents invoke dispatch_async 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 dispatch_async needs a policy

The server's purpose is to dispatch work (likely code execution tasks) into Claude Code in a devcontainer. 'dispatch_async' is almost certainly an asynchronous variant of 'dispatch', which triggers external operations or code execution. The description is empty, reducing confidence, but the naming pattern and server context strongly suggest Execute category.

From the tool's definition Tool name 'dispatch_async' on a server described as dispatching work into Claude Code running inside a devcontainer over stdio. Sibling tool 'dispatch' strongly implies execution of tasks/commands.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dispatch_async Rate-limited

dispatch_async 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": {
    "dispatch_async": {
      "limits": [
        {
          "counter": "dispatch_async_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 dispatch_async

What does the dispatch_async tool do? +

dispatch_async. 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 dispatch_async? +

Register the Claude Bridge MCP server in PolicyLayer and add a rule for dispatch_async: 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 dispatch_async? +

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

Can I rate-limit dispatch_async? +

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

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

dispatch_async 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.