// SCAN REPORT

Claude Session Continuity

77 tools. 34 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 30 Jun 2026

34 can modify or destroy data

43 read-only

77 tools total

Community server · catalogue entry verified 30/06/2026

How to control Claude Session Continuity ↓

TOOL MAP

What Claude Session Continuity exposes to your agents

Read (43) Write / Execute (32) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Claude Session Continuity tools

Destructive · High delete_memory This tool permanently removes memory/context data without the possibility of reversal. Destructive · High memory_delete This tool permanently deletes memory entries and their associated embeddings without apparent recovery mechanism. Execute · High run_verification This tool executes build processes, test suites, and linting operations—external operations whose effects depend on the project state and configuration. Execute · High verify_all The tool explicitly runs shell commands (build, test, lint) on the host system.

34 of Claude Session Continuity's 77 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Claude Session Continuity

PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Session Continuity, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_memory": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_task": {
    "limits": [
      {
        "counter": "add_task_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "context_get": {
    "limits": [
      {
        "counter": "context_get_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Claude Session Continuity — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CLAUDE SESSION CONTINUITY →

Instant setup, no code required.

FULL CATALOGUE

All 77 Claude Session Continuity tools

DESTRUCTIVE 2 tools

Destructive delete_memory 메모리를 삭제합니다. Destructive memory_delete 메모리 삭제. 관련 임베딩도 함께 삭제됩니다.

EXECUTE 3 tools

Execute run_verification 프로젝트의 빌드/테스트/린트를 한 번에 실행하고 결과를 반환합니다. Execute verify 프로젝트 검증 (빌드/테스트/린트). - gates: 실행할 게이트 배열 (기본: 전체) - build: 빌드 검증 - test: 테스트 실행 - lint: 린트 검사 각 게이트 결과와 Execute verify_all Run build, test, and lint sequentially for a project. Auto-detects platform-specific commands. Side effects: e

WRITE 29 tools

Write add_task 프로젝트에 태스크를 추가합니다. Write auto_learn_decision 아키텍처/기술 결정 사항을 자동 기록합니다. 왜 이 선택을 했는지 기록하여 나중에 참조할 수 있습니다. Write auto_learn_dependency 의존성 변경 사항을 자동 기록합니다. 버전 충돌이나 업그레이드 시 참조합니다. Write auto_learn_fix 에러/버그 해결 방법을 자동 기록합니다. 비슷한 에러 발생 시 참조할 수 있습니다. Write auto_learn_pattern 프로젝트의 코드 패턴/컨벤션을 자동 기록합니다. 일관성 유지에 활용됩니다. Write collect_work_feedback /work 작업 완료 시 자동으로 피드백을 수집합니다. 에러, 타임아웃, 불편사항 등을 기록합니다. Write complete_task 태스크를 완료 처리합니다. Write context_update 프로젝트 컨텍스트 업데이트. 작업 종료 시 호출. - currentState: 현재 상태 1줄 요약 (필수) - recentFiles: 최근 수정 파일 (최대 10개) - blockers: 블로커/ Write create_relation 두 메모리 간의 관계를 생성합니다. (지식 그래프) Write graph_connect Create a directed edge between two memories in the knowledge graph. Supports 7 relation types for structured k Write init_project_context 새 프로젝트의 고정 컨텍스트를 초기화합니다. plan.md 기반으로 자동 추출하거나 직접 입력. Write learn 자동 학습 (결정/수정/패턴/의존성). type에 따라 다른 정보 저장: - decision: 기술 결정 (alternatives 포함) - fix: 버그 수정 (solution, preventio Write memory_store Store a piece of knowledge in the memory system. Memories are typed (observation, decision, learning, error, p Write project_init Initialize a new project in the continuity system. Creates records in the project_context and active_context t Write record_filter_pattern API content filtering에 걸린 패턴을 기록합니다. 비슷한 상황 회피에 사용됩니다. Write record_solution 에러 해결 방법을 기록합니다. 에러 해결 후 호출하면 나중에 같은 에러 시 참조 가능. Write record_work_pattern 자주 사용하는 작업 패턴을 기록합니다. Write resolve_feedback 피드백을 해결 완료 처리합니다. Write save_session_history 세션 기록을 DB에 저장합니다. update_session 호출 시 자동으로 호출됩니다. Write session_end Save the current session state before ending a conversation. Persists a summary, completed work, next steps, m Write solution_record Record an error-solution pair in the solution archive. Associates an error signature (the searchable key), opt Write store_memory 새로운 지식/학습/결정 사항을 메모리에 저장합니다. Claude가 배운 것들을 기억합니다. Write task_add Add a new task to a project\ Write task_manage 태스크 관리 (추가/완료/업데이트/목록). action에 따라 다른 동작: - add: 새 태스크 추가 (title 필수) - complete: 태스크 완료 (taskId 필수) - update: Write task_update Update a task\ Write update_active_context 프로젝트의 활성 컨텍스트를 업데이트합니다. 작업 종료 시 호출. Write update_architecture_decision 프로젝트에 아키텍처 결정을 추가합니다. 중요한 기술 결정 시 호출. Write update_session 프로젝트의 SESSION.md를 업데이트하고 DB에 이력을 저장합니다. Write update_task_status 태스크 상태를 변경합니다.

READ 43 tools

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Claude Session Continuity

Can an AI agent delete data through the Claude Session Continuity MCP server? +

Yes. The Claude Session Continuity server exposes 2 destructive tools including delete_memory, memory_delete. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Claude Session Continuity? +

The Claude Session Continuity server has 29 write tools including add_task, auto_learn_decision, auto_learn_dependency. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Claude Session Continuity.

How many tools does the Claude Session Continuity MCP server expose? +

77 tools across 4 categories: Destructive, Execute, Read, Write. 43 are read-only. 34 can modify, create, or delete data.

How do I enforce a policy on Claude Session Continuity? +

Register the Claude Session Continuity MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Claude Session Continuity tool call.

Deterministic rules across all 77 Claude Session Continuity tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLAUDE SESSION CONTINUITY →

Instant setup, no code required.

77 Claude Session Continuity tools catalogued and risk-classified — across an index of 43,000+ MCP servers.