recall_mementos
AI agents call recall_mementos to retrieve information from MCP Memento without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'recall' operation is a standard data retrieval action that queries the memory store without modifying, deleting, or executing anything. Despite the empty tool description lowering confidence slightly, the contextual evidence from the server's purpose (memory storage and retrieval system) and the term 'recall' strongly indicate a Read category with low severity.
From the tool's definition Tool name 'recall_mementos' indicates retrieval of stored memory items. The server description emphasizes 'storing and recalling solutions, facts, and decisions', and 'recall' is a retrieval operation.
Attacks that exploit this kind of access
recall_mementos. It is categorised as a Read tool in the MCP Memento MCP Server, which means it retrieves data without modifying state.
Register the MCP Memento MCP server in PolicyLayer and add a rule for recall_mementos: 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 MCP Memento. Nothing to install.
recall_mementos 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 recall_mementos 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 recall_mementos. 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.
recall_mementos is provided by the MCP Memento MCP server (x-hannibal/mcp-memento). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →