dispatch · Claude Bridge MCP: Risk & Policy

WHAT IT DOES

What dispatch does on Claude Bridge

AI agents invoke dispatch 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 needs a policy

The server's purpose is to dispatch work/tasks into a running Claude Code instance inside a devcontainer. 'dispatch' almost certainly triggers execution of code or commands in that environment. The empty description lowers confidence, but the context (sibling tools like dispatch_async, cancel_dispatch, list_jobs, list_completions) strongly implies this is an Execute-category tool.

From the tool's definition Tool name 'dispatch' on a server described as dispatching work into Claude Code running inside a devcontainer over stdio; sibling tools include 'dispatch_async', 'cancel_dispatch' suggesting execution of tasks/jobs

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dispatch Rate-limited

dispatch 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": {
      "limits": [
        {
          "counter": "dispatch_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

What does the dispatch tool do? +

dispatch. 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? +

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

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

Can I rate-limit dispatch? +

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

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

dispatch 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.