AI agents call memory_search_bm25 to retrieve information from Mementos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs full-text search using BM25 ranking to query memories and return scored results. It is purely a read/retrieval operation with no capability to create, modify, delete, or execute operations. The search functionality has minimal blast radius if misused by an agent—it may retrieve unwanted information but cannot alter or harm the memory store.
From the tool's definition Tool name is 'memory_search_bm25' and description states it 'Search memories using FTS5 BM25 ranking. Returns results scored by term frequency...' - this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Search memories using FTS5 BM25 ranking. Returns results scored by term frequency, document length, and field weights (key=10, value=5, summary=3). It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.
Register the Mementos MCP server in PolicyLayer and add a rule for memory_search_bm25: 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 Mementos. Nothing to install.
memory_search_bm25 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 memory_search_bm25 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 memory_search_bm25. 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.
memory_search_bm25 is provided by the Mementos MCP server (@hasna/mementos). 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 →