Medium Risk

codex_create_project

Create a new project in the organization

How to control codex_create_project ↓

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

Medium Risk

This tool creates a new project, which is a reversible write operation. It does not delete data or execute code. Severity is medium because creating projects in an organization can affect organizational structure, permissions, and resource allocation, but it is generally reversible by deleting the project afterward.

From the tool's definition "Create a new project in the organization"

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

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "codex_create_project": {
      "limits": [
        {
          "counter": "codex_create_project_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

codex_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.

  1. Create a free account and register Sage MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the codex_create_project tool do? +

Create a new project in the organization. It is categorised as a Write tool in the Sage 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 codex_create_project? +

Register the Sage MCP server in PolicyLayer and add a rule for codex_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 Sage MCP. Nothing to install.

What risk level is codex_create_project? +

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

Can I rate-limit codex_create_project? +

Yes. Add a rate_limit block to the codex_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 codex_create_project completely? +

Set action: deny in the PolicyLayer policy for codex_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 codex_create_project? +

codex_create_project is provided by the Sage MCP server (sagemcp/sagemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Sage MCP tool call.

Deterministic rules across all 359 Sage MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

359 Sage MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.