비슷한 에러의 해결 방법을 검색합니다. 에러 발생 시 먼저 호출하여 기존 솔루션 확인.
AI agents call find_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.
The tool retrieves and queries existing error solutions from a knowledge base. It has no side effects—it does not create, modify, delete, or execute any operations. The word 'search' (검색) confirms a pure read operation. Severity is low because querying historical solutions cannot damage systems or data.
From the tool's definition Tool description states it 'searches for solutions to similar errors' (find_solution, 검색합니다) and 'checks existing solutions when errors occur'. This is a read operation that queries historical data without modifying it.
Attacks that exploit this kind of access
비슷한 에러의 해결 방법을 검색합니다. 에러 발생 시 먼저 호출하여 기존 솔루션 확인. 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 find_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.
find_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 find_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 find_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.
find_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 →