route_to_agent · Scrumdo MCP: Risk & Policy

WHAT IT DOES

What route_to_agent does on Scrumdo

AI agents invoke route_to_agent to trigger actions in Scrumdo. 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 route_to_agent needs a policy

The tool delegates/routes tasks to agents for execution across multiple phases (plan, implement, verify, integrate). This triggers external agent operations whose effects depend on arguments, making it an Execute category tool. The description is truncated, reducing confidence, but routing/delegating to agents that can implement and integrate code carries high blast radius if misused.

From the tool's definition Delegate a loop task type ('plan'|'implement'|'verify'|'integrate') to

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

route_to_agent Rate-limited

route_to_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": {
    "route_to_agent": {
      "limits": [
        {
          "counter": "route_to_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 Scrumdo, so you can run agents against it safely.

FAQ

Questions about route_to_agent

What does the route_to_agent tool do? +

Delegate a loop task type ('plan'|'implement'|'verify'|'integrate') to. It is categorised as a Execute tool in the Scrumdo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on route_to_agent? +

Register the Scrumdo MCP server in PolicyLayer and add a rule for route_to_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 Scrumdo. Nothing to install.

What risk level is route_to_agent? +

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

Can I rate-limit route_to_agent? +

Yes. Add a rate_limit block to the route_to_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 route_to_agent completely? +

Set action: deny in the PolicyLayer policy for route_to_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 route_to_agent? +

route_to_agent is provided by the Scrumdo MCP server (scrumdollc/scrumdo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.