create_agent · Mistral Agent Manager MCP: Risk & Policy

WHAT IT DOES

What create_agent does on Mistral Agent Manager

AI agents use create_agent to create or update resources in Mistral Agent Manager — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mistral Agent Manager environment.

WHY IT NEEDS A POLICY

Why create_agent needs a policy

This tool creates new agents, which is a reversible modification of system state. It does not execute arbitrary code, delete data irreversibly, or move money. The blast radius is medium because an AI agent could create numerous agents or agents with unintended configurations, but the action is reversible via the sibling delete_agent tool. Confidence is high due to explicit creation semantics in name and description.

From the tool's definition Tool name 'create_agent' and description 'Create a new Mistral agent' indicate data creation. Server context shows this integrates with Mistral API for agent management.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_agent Rate-limited

create_agent 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_agent": {
      "limits": [
        {
          "counter": "create_agent_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mistral Agent Manager, so you can run agents against it safely.

FAQ

Questions about create_agent

What does the create_agent tool do? +

Create a new Mistral agent. It is categorised as a Write tool in the Mistral Agent Manager MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_agent? +

Register the Mistral Agent Manager MCP server in PolicyLayer and add a rule for create_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 Mistral Agent Manager. Nothing to install.

What risk level is create_agent? +

create_agent is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_agent? +

Yes. Add a rate_limit block to the create_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 create_agent completely? +

Set action: deny in the PolicyLayer policy for create_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 create_agent? +

create_agent is provided by the Mistral Agent Manager MCP server (uzbyr/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.