dispatch_agent · MCP Claude Code MCP: Risk & Policy

WHAT IT DOES

What dispatch_agent does on MCP Claude Code

AI agents invoke dispatch_agent to trigger actions in MCP Claude Code. 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_agent needs a policy

The server-level description explicitly mentions executing commands and modifying files. 'dispatch_agent' suggests spawning or delegating work to a sub-agent, which on such a server likely involves executing operations (code analysis, file modification, command execution). With sibling tools like edit, multi_edit, content_replace, and no description to narrow scope, the most plausible interpretation is Execute.

From the tool's definition Tool name 'dispatch_agent' on a server that 'execute commands' and 'manage projects through direct file system interactions'; tool description is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dispatch_agent Rate-limited

dispatch_agent 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_agent": {
      "limits": [
        {
          "counter": "dispatch_agent_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 MCP Claude Code, so you can run agents against it safely.

FAQ

Questions about dispatch_agent

What does the dispatch_agent tool do? +

dispatch_agent. It is categorised as a Execute tool in the MCP Claude Code 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_agent? +

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

What risk level is dispatch_agent? +

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

Can I rate-limit dispatch_agent? +

Yes. Add a rate_limit block to the dispatch_agent 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_agent completely? +

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

dispatch_agent is provided by the MCP Claude Code MCP server (sdglbl/mcp-claude-code). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.