Find memories similar to a specific memory
AI agents call find_similar_memories to retrieve information from Claude Memory Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries existing memories based on similarity matching. It has no side effects—it does not create, modify, delete, or execute code. Even though it accesses potentially sensitive memory data, the core capability is read-only information retrieval.
From the tool's definition Tool name is 'find_similar_memories' and description states 'Find memories similar to a specific memory'. This performs a search/query operation to retrieve data without modifying or deleting anything.
Attacks that exploit this kind of access
Find memories similar to a specific memory. It is categorised as a Read tool in the Claude Memory Server MCP Server, which means it retrieves data without modifying state.
Register the Claude Memory Server MCP server in PolicyLayer and add a rule for find_similar_memories: 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 Claude Memory Server. Nothing to install.
find_similar_memories 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_memories 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_memories. 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_memories is provided by the Claude Memory Server MCP server (xiy/claude-memory-server). 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 →