route_task · Oxide MCP: Risk & Policy

WHAT IT DOES

What route_task does on Oxide

AI agents invoke route_task to trigger actions in Oxide. 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_task needs a policy

The server is an LLM orchestrator that routes tasks to various AI models and services. 'route_task' likely triggers execution of tasks on external AI services (Gemini, Qwen, Ollama, LM Studio), constituting an Execute-category action. However, the description is empty, so confidence is reduced.

From the tool's definition Tool name 'route_task' combined with server description mentioning routing tasks to AI models, distributed processing, and parallel execution across local and network services.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

route_task Rate-limited

route_task 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_task": {
      "limits": [
        {
          "counter": "route_task_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 Oxide, so you can run agents against it safely.

FAQ

Questions about route_task

What does the route_task tool do? +

route_task. It is categorised as a Execute tool in the Oxide 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_task? +

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

What risk level is route_task? +

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

Can I rate-limit route_task? +

Yes. Add a rate_limit block to the route_task 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_task completely? +

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

route_task is provided by the Oxide MCP server (yayoboy/oxide). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.