프로젝트 컨텍스트 조회. 새 세션 시작 시 필수 호출. - 고정 컨텍스트: 기술 스택, 아키텍처 결정, 코드 패턴 - 활성 컨텍스트: 현재 상태, 최근 파일, 블로커 - 미완료 태스크 (최대 3개) ~650토큰으로 압축된 프로젝트 정보 반환.
AI agents call context_get 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 queries and retrieves existing session/project metadata without creating, modifying, deleting, or executing external operations. It is a passive information retrieval mechanism used to restore project state at session start. No side effects or state changes are described. Blast radius of misuse is minimal — an agent could learn about the project, but cannot act on that knowledge through this tool alone.
From the tool's definition Tool name 'context_get' and description indicate retrieval of project context information: 'retrieves project context', 'returns compressed project information'. Verbs used are 'get', 'retrieve', 'call' with no modification or deletion.
Attacks that exploit this kind of access
프로젝트 컨텍스트 조회. 새 세션 시작 시 필수 호출. - 고정 컨텍스트: 기술 스택, 아키텍처 결정, 코드 패턴 - 활성 컨텍스트: 현재 상태, 최근 파일, 블로커 - 미완료 태스크 (최대 3개) ~650토큰으로 압축된 프로젝트 정보 반환. 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 context_get: 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.
context_get 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 context_get 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 context_get. 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.
context_get 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 →