Retrieve code artifact by ID with complete details. WHEN: You need the full code implementation and metadata for a specific artifact. Common after listing artifacts or when a memory references an artifact ID. BEHAVIOR: Returns complete artifact including full code content, description, and metada...
AI agents call get_code_artifact to retrieve information from Forgetful without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries stored code artifacts by ID with no side effects. It performs a read-only operation that returns existing data without creating, modifying, deleting, executing, or causing financial impact. The ownership verification is a safeguard, not an action that changes state. Classification as Read is appropriate for a straightforward data retrieval operation on a knowledge base storage system.
From the tool's definition Tool name is 'get_code_artifact' and description states 'Retrieve code artifact by ID with complete details.' The behavior explicitly returns data without modification: 'Returns complete artifact including full code content, description, and metadata.' The…
Documented attack patterns abuse exactly the kind of access get_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 get_code_artifact:
{
"version": "1",
"default": "deny",
"tools": {
"get_code_artifact": {}
}
}get_code_artifact is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve code artifact by ID with complete details. WHEN: You need the full code implementation and metadata for a specific artifact. Common after listing artifacts or when a memory references an artifact ID. BEHAVIOR: Returns complete artifact including full code content, description, and metadata. Ownership verified automatically. NOT-USE: For browsing multiple artifacts (use list_code_artifacts). Args: artifact_id: Unique code artifact ID ctx: Context (automatically injected) Returns: Complete CodeArtifact with code, description, metadata Raises: ToolError if artifact not found or access denied. It is categorised as a Read tool in the Forgetful MCP Server, which means it retrieves data without modifying state.
Register the Forgetful MCP server in PolicyLayer and add a rule for get_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.
get_code_artifact is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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.
Set action: deny in the PolicyLayer policy for get_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.
get_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.
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.