Find memories semantically similar to a given text or to an existing memory. Useful for deduplication before adding new rules.
AI agents call find_similar to retrieve information from mcp-Agentmemory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic search across stored memories using hybrid search capabilities (BM25 + pgvector). It queries existing data and returns matches without side effects. The stated use case of 'deduplication before adding new rules' confirms it is preparatory and read-only. No data is created, modified, deleted, or executed—only retrieved based on similarity metrics.
From the tool's definition The tool 'Find memories semantically similar to a given text or to an existing memory' retrieves and queries data without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Find memories semantically similar to a given text or to an existing memory. Useful for deduplication before adding new rules. It is categorised as a Read tool in the mcp-Agentmemory MCP Server, which means it retrieves data without modifying state.
Register the mcp-Agentmemory MCP server in PolicyLayer and add a rule for 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 mcp-Agentmemory. Nothing to install.
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 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 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.
find_similar is provided by the mcp-Agentmemory MCP server (obidel/agentmemory). 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 →