과거에 비슷한 작업을 했는지 검색합니다. 이전 작업 패턴을 참고할 때 유용합니다.
AI agents call search_similar_work 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 a read-only search operation across past work history to retrieve and reference similar patterns. It has no side effects—it only retrieves data for informational purposes. No data is modified, deleted, executed, or financially impacted. The low severity reflects minimal risk even if misused, as searching historical data cannot cause harm or unintended consequences.
From the tool's definition Tool name 'search_similar_work' and description 'searches if similar work was done in the past' (translated from Korean) indicates a query/search operation that retrieves historical work patterns without modifying or executing anything.
Attacks that exploit this kind of access
과거에 비슷한 작업을 했는지 검색합니다. 이전 작업 패턴을 참고할 때 유용합니다. 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 search_similar_work: 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.
search_similar_work 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 search_similar_work 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 search_similar_work. 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.
search_similar_work 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 →