create_project · AgentCortex MCP: Risk & Policy

WHAT IT DOES

What create_project does on AgentCortex MCP

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

WHY IT NEEDS A POLICY

Why create_project needs a policy

This tool creates new data (a project) in a reversible manner. It organizes memories and tasks without executing code, deleting data, or affecting financial systems. The blast radius of misuse is minimal—a rogue agent could create many projects, but this is easily remediated by deletion or cleanup. This is a straightforward Write operation.

From the tool's definition Tool name 'create_project' and description 'Create a new project' explicitly performs creation of a new entity (a project). Description states it is for organizing information and does not indicate any destructive, financial, or code execution capabilities.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_project Rate-limited

create_project 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_project": {
      "limits": [
        {
          "counter": "create_project_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 AgentCortex MCP, so you can run agents against it safely.

FAQ

Questions about create_project

What does the create_project tool do? +

Create a new project to organize memories and tasks. Projects help separate different work contexts and make it easier to find relevant information. It is categorised as a Write tool in the AgentCortex MCP 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_project? +

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

What risk level is create_project? +

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

Can I rate-limit create_project? +

Yes. Add a rate_limit block to the create_project 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_project completely? +

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

create_project is provided by the AgentCortex MCP server (sage-hq/agentcortex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.