delegate_to_model

THE RISK

High Risk

Why delegate_to_model needs a policy

This tool triggers execution of tasks by routing them to external AI models. It initiates external operations whose effects depend on the task arguments provided. The blast radius depends on what task is delegated — it could range from benign queries to code execution or destructive operations, making it medium severity by default since the tool itself is an orchestration/dispatch mechanism rather than directly…

From the tool's definition Route a task to the optimal model based on capability matching

Documented attack patterns abuse exactly the kind of access delegate_to_model gives an agent:

POLICY

How to control delegate_to_model

PolicyLayer is an MCP gateway — it sits between your AI agents and Nexus Agents, and nothing reaches the server without passing your rules. This is the rule we recommend for delegate_to_model:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "delegate_to_model": {
      "limits": [
        {
          "counter": "delegate_to_model_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

delegate_to_model 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.

Create a free account and register Nexus Agents — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Nexus Agents tools

Execute execute_expert Execute a task using a previously created expert agent Execute run_workflow Execute a workflow template with provided inputs Execute orchestrate Orchestrate a task by analyzing it and coordinating expert agents Write consensus_vote Submit a vote in a multi-agent consensus decision process Write create_expert Create a specialized expert agent for code, architecture, or security tasks Read list_experts List available expert types that can be created with create_expert Read list_workflows List available workflow templates Other my_tool my_tool

All 9 Nexus Agents tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Nexus Agents → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about delegate_to_model

What does the delegate_to_model tool do? +

Route a task to the optimal model based on capability matching. It is categorised as a Execute tool in the Nexus Agents MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on delegate_to_model? +

Register the Nexus Agents MCP server in PolicyLayer and add a rule for delegate_to_model: 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 Nexus Agents. Nothing to install.

What risk level is delegate_to_model? +

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

Can I rate-limit delegate_to_model? +

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

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

delegate_to_model is provided by the Nexus Agents MCP server (nexus-substrate/nexus-agents). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Nexus Agents tool call.

Start from Nexus Agents, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →