프로젝트 목록 및 통계 조회. - project 없으면: 전체 프로젝트 목록 - project 있으면: 해당 프로젝트 상세 정보 각 프로젝트의 플랫폼, 최근 활동, 태스크 현황 포함.
AI agents call projects 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 only queries and retrieves project metadata and statistics. It performs read-only operations returning project lists and details without creating, modifying, deleting, or executing any operations. No side effects are indicated.
From the tool's definition Tool description indicates it 'retrieves or queries data' - '프로젝트 목록 및 통계 조회' (project list and statistics inquiry), '전체 프로젝트 목록' (entire project list), '해당 프로젝트 상세 정보' (project details).
Attacks that exploit this kind of access
프로젝트 목록 및 통계 조회. - project 없으면: 전체 프로젝트 목록 - project 있으면: 해당 프로젝트 상세 정보 각 프로젝트의 플랫폼, 최근 활동, 태스크 현황 포함. 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 projects: 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.
projects 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 projects 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 projects. 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.
projects 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 →