유사 이슈 해결 방법 검색. 에러 메시지나 이슈 설명으로 과거 해결 사례 검색. FTS + 시맨틱 검색으로 유사 이슈 찾기.
AI agents call recall_solution 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 tool performs read-only retrieval of historical solution data based on error messages or issue descriptions. It queries a knowledge base to find similar past issues and their resolutions. There are no side effects, data modifications, code execution, or destructive operations.
From the tool's definition Tool searches and retrieves past solutions ('유사 이슈 해결 방법 검색' = 'search for similar issue resolution methods'; 'FTS + 시맨틱 검색으로 유사 이슈 찾기' = 'find similar issues using FTS + semantic search').
Attacks that exploit this kind of access
유사 이슈 해결 방법 검색. 에러 메시지나 이슈 설명으로 과거 해결 사례 검색. FTS + 시맨틱 검색으로 유사 이슈 찾기. 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_solution: 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_solution 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_solution 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_solution. 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_solution 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 →