Create a specialized expert agent for code, architecture, or security tasks
AI agents use create_expert to create or update resources in Nexus Agents — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nexus Agents environment.
The tool creates a new persistent expert agent entity within the nexus-agents system. This is a Write operation as it creates a new resource (expert agent configuration) that can presumably be modified or deleted later. It does not execute code directly, delete data, or involve financial transactions.
From the tool's definition "Create a specialized expert agent" — the tool creates a new agent/configuration resource
Documented attack patterns abuse exactly the kind of access create_expert gives an agent:
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 create_expert:
{
"version": "1",
"default": "deny",
"tools": {
"create_expert": {
"limits": [
{
"counter": "create_expert_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_expert stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a specialized expert agent for code, architecture, or security tasks. It is categorised as a Write tool in the Nexus Agents MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nexus Agents MCP server in PolicyLayer and add a rule for create_expert: 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.
create_expert is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_expert 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.
Set action: deny in the PolicyLayer policy for create_expert. 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.
create_expert 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.
Start from Nexus Agents, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Nexus Agents tools catalogued and risk-classified — across an index of 43,000+ MCP servers.