프로젝트 컨텍스트 업데이트. 작업 종료 시 호출. - currentState: 현재 상태 1줄 요약 (필수) - recentFiles: 최근 수정 파일 (최대 10개) - blockers: 블로커/이슈 (없으면 생략) - verification: 마지막 검증 결과 (passed/failed) - architectureDecision: 새로운 아키텍처 결정
AI agents use context_update to create or update resources in Claude Session Continuity — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Session Continuity environment.
This tool creates or modifies session continuity metadata and project context information. While the modifications are reversible (can be updated again or reverted), they affect stored project state and decision history. The impact is bounded to project metadata rather than core application data or external systems, making it Write rather than Execute or higher severity.
From the tool's definition Tool description indicates it 'updates' project context with parameters like 'currentState', 'recentFiles', 'blockers', and 'architectureDecision'. The verb 'update' and the act of modifying stored project state qualifies as a reversible modification of data.
Attacks that exploit this kind of access
프로젝트 컨텍스트 업데이트. 작업 종료 시 호출. - currentState: 현재 상태 1줄 요약 (필수) - recentFiles: 최근 수정 파일 (최대 10개) - blockers: 블로커/이슈 (없으면 생략) - verification: 마지막 검증 결과 (passed/failed) - architectureDecision: 새로운 아키텍처 결정. It is categorised as a Write tool in the Claude Session Continuity MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Session Continuity MCP server in PolicyLayer and add a rule for context_update: 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_update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the context_update 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_update. 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_update 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 →