Find memories similar to a given memory or text using vector similarity. Uses pure semantic similarity (vector distance) to find related memories. This is different from hybrid search - it finds memories with similar meaning, even if they don
AI agents call remember_find_similar to retrieve information from Remember without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs semantic search over stored memories to retrieve related items based on vector distance. It has no side effects beyond returning read-only query results. While it operates on a multi-tenant system, the action itself is purely informational retrieval with no capability to modify, delete, or execute operations.
From the tool's definition Tool description states it "Find[s] memories similar to a given memory or text using vector similarity" and "find[s] memories with similar meaning." This is a query operation with no modification, creation, deletion, or execution of external code.
Attacks that exploit this kind of access
Find memories similar to a given memory or text using vector similarity. Uses pure semantic similarity (vector distance) to find related memories. This is different from hybrid search - it finds memories with similar meaning, even if they don. It is categorised as a Read tool in the Remember MCP Server, which means it retrieves data without modifying state.
Register the Remember MCP server in PolicyLayer and add a rule for remember_find_similar: 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 Remember. Nothing to install.
remember_find_similar 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 remember_find_similar 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 remember_find_similar. 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.
remember_find_similar is provided by the Remember MCP server (@prmichaelsen/remember-mcp). 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 →