dispatch_downstream_tool · Maple MCP: Risk & Policy

WHAT IT DOES

What dispatch_downstream_tool does on Maple

AI agents invoke dispatch_downstream_tool to trigger actions in Maple. 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_downstream_tool needs a policy

This tool executes arbitrary tool calls against downstream MCP applications. The actual effect depends entirely on which downstream tools are invoked — they could be destructive, financial, or otherwise high-impact.

From the tool's definition Dispatch a tool call to one or more downstream MCP apps via Maple in execution order

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dispatch_downstream_tool Rate-limited

dispatch_downstream_tool 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_downstream_tool": {
      "limits": [
        {
          "counter": "dispatch_downstream_tool_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 Maple, so you can run agents against it safely.

FAQ

Questions about dispatch_downstream_tool

What does the dispatch_downstream_tool tool do? +

Dispatch a tool call to one or more downstream MCP apps via Maple in execution order, then normalize, score, and log outputs into Maple traces. It is categorised as a Execute tool in the Maple 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_downstream_tool? +

Register the Maple MCP server in PolicyLayer and add a rule for dispatch_downstream_tool: 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 Maple. Nothing to install.

What risk level is dispatch_downstream_tool? +

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

Can I rate-limit dispatch_downstream_tool? +

Yes. Add a rate_limit block to the dispatch_downstream_tool 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_downstream_tool completely? +

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

dispatch_downstream_tool is provided by the Maple MCP server (omar2001ramadan/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.