Search memories using both text and semantic similarity
AI agents call hybrid_search_memory 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.
This tool retrieves and queries stored memories using combined text and semantic search methods. It has no side effects, does not create, modify, or delete data, and does not execute code or trigger external operations. It is a straightforward data retrieval mechanism, placing it squarely in the Read category.
From the tool's definition The tool 'hybrid_search_memory' is described as 'Search memories using both text and semantic similarity' — it performs a search/query operation that retrieves data without modifying, deleting, or executing external code.
Attacks that exploit this kind of access
Search memories using both text and semantic similarity. 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 hybrid_search_memory: 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.
hybrid_search_memory 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 hybrid_search_memory 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 hybrid_search_memory. 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.
hybrid_search_memory 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 →