Retreive complete memory details by ID WHEN: You require the full details of a specific memory and you already have an ID, for example from receiving a list of linked memories from a project, document or code artifact. BEHAVIOUR: Returns the complete memory object or an error if the memory is not...
AI agents call get_memory 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 performs a straightforward read operation: it fetches and returns an existing memory object by ID. There are no modifications, deletions, or external side effects. The user must already possess the memory ID, making it a simple lookup operation. This is consistent with the Read category for tools that retrieve or query data without side effects.
From the tool's definition Tool description states 'Retrieve complete memory details by ID' and 'Returns the complete memory object'. The NOT-USE section explicitly excludes searching, listing, updating, or creating—confirming this is retrieval-only with no side effects.
Documented attack patterns abuse exactly the kind of access get_memory 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_memory:
{
"version": "1",
"default": "deny",
"tools": {
"get_memory": {}
}
}get_memory 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.
Retreive complete memory details by ID WHEN: You require the full details of a specific memory and you already have an ID, for example from receiving a list of linked memories from a project, document or code artifact. BEHAVIOUR: Returns the complete memory object or an error if the memory is not found or does not belong to the user NOT-USE: Searching for memories using natural language (use query_memory), listing all memories, updating (use update_memory) or creating (use create_memory) Args: memory_id: ID of the memory to retrieve Returns: Complete memory object, or error if not found or does not belong to the user. 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_memory: 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_memory 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_memory 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_memory. 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_memory 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.