Search memories using semantic similarity (requires Ollama)
AI agents call semantic_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 data from memory storage without creating, modifying, deleting, or executing any actions. It is purely a search/retrieval mechanism. No side effects are introduced by searching. The low severity reflects that misuse would only expose existing stored information rather than cause irreversible damage, data modification, or execute arbitrary code.
From the tool's definition Tool performs a search operation using semantic similarity to query stored memories, with no modification, deletion, or execution capabilities mentioned.
Attacks that exploit this kind of access
Search memories using semantic similarity (requires Ollama). 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 semantic_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.
semantic_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 semantic_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 semantic_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.
semantic_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 →