키워드로 관련 메모리를 검색합니다. FTS5 전체 텍스트 검색을 사용합니다.
AI agents call recall_memory 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.
The tool searches and retrieves stored memories/context based on keywords. Full-text search (FTS5) is a read-only operation that queries existing data. No creation, modification, deletion, code execution, or financial operations are involved. This falls squarely in the Read category with low severity because misuse would only retrieve potentially sensitive context, not modify or destroy it.
From the tool's definition Tool description: 'recalls memory using keyword search' and 'uses FTS5 full-text search' — these are query operations that retrieve data without modification or side effects.
Attacks that exploit this kind of access
키워드로 관련 메모리를 검색합니다. FTS5 전체 텍스트 검색을 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 recall_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 Session Continuity. Nothing to install.
recall_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 recall_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 recall_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.
recall_memory 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 →