Medium Risk

create_code_artifact

create_code_artifact

How to control create_code_artifact ↓

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

Medium Risk

The tool creates code artifacts in a persistent knowledge base. This is a Write operation (creates/modifies data reversibly) rather than Read, Execute, Destructive, or Financial. Severity is medium because misuse could clutter the knowledge base or create malicious code artifacts, but the action is reversible (evidenced by the sibling delete_code_artifact tool).

From the tool's definition Tool name is 'create_code_artifact' with empty description. Sibling tools on this server include 'create_document', 'create_entity', 'create_memory', etc., establishing a pattern of Write operations (create_*) and destructive operations (delete_*).

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

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

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

create_code_artifact 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 Forgetful — 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 create_code_artifact tool do? +

create_code_artifact. It is categorised as a Write tool in the Forgetful 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_code_artifact? +

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

What risk level is create_code_artifact? +

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

Can I rate-limit create_code_artifact? +

Yes. Add a rate_limit block to the create_code_artifact 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_code_artifact completely? +

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

create_code_artifact is provided by the Forgetful MCP server (scottrbk/forgetful). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Forgetful tool call.

Deterministic rules across all 59 Forgetful tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

59 Forgetful 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.