forget
Soft-delete a specific memory by ID. The memory will no longer appear in recall results.
This record as markdown: /tools/adrata-starfield-mcp/forget.md
What forget does on Starfield
AI agents call forget to permanently remove resources in Starfield, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
memory_id | string | Yes | The ID of the memory to forget |
Parameters from the server's own tool schema.
Why forget is rated Critical
An AI agent that decides to call forget doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Starfield is gone. There is no undo for destructive operations.
Attacks that exploit this kind of access
The rule that runs forget safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Starfield, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For forget, this is the rule to start with:
forget is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Starfield, apply this rule, and every forget call is checked against it from then on.
Questions about forget
Soft-delete a specific memory by ID. The memory will no longer appear in recall results. It is categorised as a Destructive tool in the Starfield MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
forget accepts 1 parameter: memory_id. Required: memory_id. The full parameter table on this page comes from the server's own tool schema.
Register the Starfield MCP server in PolicyLayer and add a rule for forget: 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 Starfield. Nothing to install.
forget is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the forget 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 forget. 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.
forget is provided by the Starfield MCP server (@adrata/starfield-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Starfield, and thousands of servers like it.
Across the catalogue