현재 프로젝트의 컨텍스트 요약 조회. - 토큰 추정치 포함 - 전체 컨텍스트 스냅샷 반환 세션 중간에 컨텍스트 확인 시 사용.
AI agents call session_summary 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 data retrieval only—it fetches and displays project context information without side effects. It is purely informational, used to check context during a session. No data is created, modified, deleted, or executed. Lowest blast radius if misused by an AI agent.
From the tool's definition Tool name 'session_summary' and description indicate it 'queries' or 'retrieves' current project context summary, token estimates, and context snapshots. Keywords: '조회' (retrieval/query), 'returns' snapshot.
Attacks that exploit this kind of access
현재 프로젝트의 컨텍스트 요약 조회. - 토큰 추정치 포함 - 전체 컨텍스트 스냅샷 반환 세션 중간에 컨텍스트 확인 시 사용. 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 session_summary: 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.
session_summary 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 session_summary 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 session_summary. 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.
session_summary 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 →