프로젝트의 플랫폼을 자동 감지합니다 (Web, Android, Flutter, Server).
AI agents call detect_platform 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 platform detection by analyzing project metadata or structure—a query operation that returns information about the project's platform (Web, Android, Flutter, Server). No data is modified, no code is executed, and no destructive actions are possible.
From the tool's definition The tool description states '자동 감지합니다' (automatically detects) the platform type of a project, which is a detection/analysis operation that retrieves information about project characteristics without modifying, executing code, or causing side effects.
Attacks that exploit this kind of access
프로젝트의 플랫폼을 자동 감지합니다 (Web, Android, Flutter, Server). 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 detect_platform: 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.
detect_platform 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 detect_platform 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 detect_platform. 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.
detect_platform 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 →