시맨틱 검색으로 의미적으로 유사한 메모리를 찾습니다. AI 임베딩(all-MiniLM-L6-v2)을 사용합니다.
AI agents call semantic_search to retrieve information from Claude Session Continuity without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query/search operation that retrieves data from memory without side effects. No creation, modification, deletion, or execution of external operations is described. The tool simply indexes and searches stored project context using embeddings, characteristic of Read operations.
From the tool's definition Tool name 'semantic_search' and description indicating it 'finds semantically similar memories' using AI embeddings.
Attacks that exploit this kind of access
시맨틱 검색으로 의미적으로 유사한 메모리를 찾습니다. AI 임베딩(all-MiniLM-L6-v2)을 사용합니다. It is categorised as a Read tool in the Claude Session Continuity MCP Server, which means it retrieves data without modifying state.
Register the Claude Session Continuity MCP server in PolicyLayer and add a rule for semantic_search: 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 Session Continuity. Nothing to install.
semantic_search 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 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. 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 is provided by the Claude Session Continuity MCP server (leesgit/claude-session-continuity-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 →