// SCAN REPORT

MCP Claude Context Continuity

8 tools. 6 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

6 can modify or destroy data

2 read-only

8 tools total

Community server · catalogue entry verified 03/07/2026

How to control MCP Claude Context Continuity ↓

TOOL MAP

What MCP Claude Context Continuity exposes to your agents

Read (2) Write / Execute (4) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCP Claude Context Continuity tools

Destructive · High clear_execution_history This tool permanently removes execution history records without a reversibility mechanism or undo capability. Destructive · High reset_session Resetting a session implies irreversibly clearing the current session state, including conversation context and history accumulated within that session. Execute · High execute_claude This tool runs the Claude CLI, which can trigger external operations and computational processes whose effects depend on the arguments passed. Execute · High execute_claude_with_context This tool triggers execution of the Claude CLI with potentially user-controlled file context arguments.

6 of MCP Claude Context Continuity's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Claude Context Continuity

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

Deny destructive operations

{
  "clear_execution_history": {
    "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

{
  "set_current_session": {
    "limits": [
      {
        "counter": "set_current_session_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_current_session": {
    "limits": [
      {
        "counter": "get_current_session_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 MCP Claude Context 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 MCP CLAUDE CONTEXT CONTINUITY →

Instant setup, no code required.

FULL CATALOGUE

All 8 MCP Claude Context Continuity tools

DESTRUCTIVE 2 tools

Destructive clear_execution_history 実行履歴をクリア Destructive reset_session セッションをリセット

EXECUTE 3 tools

Execute execute_claude Claude CLIを実行して結果を返す Execute execute_claude_with_context ファイルコンテキスト付きでClaude CLIを実行 Execute test_claude_cli Claude CLIが正しく設定されているかテスト

WRITE 1 tools

Write set_current_session セッションIDを即座に設定（実行は一瞬で完了）

READ 2 tools

Read get_current_session 現在のセッションIDを取得 Read get_execution_history 実行履歴を取得

EXPLORE

Related servers

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

FAQ

Questions about MCP Claude Context Continuity

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

Yes. The MCP Claude Context Continuity server exposes 2 destructive tools including clear_execution_history, reset_session. 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 MCP Claude Context Continuity? +

The MCP Claude Context Continuity server has 1 write tools including set_current_session. 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 MCP Claude Context Continuity.

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

8 tools across 4 categories: Destructive, Execute, Read, Write. 2 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on MCP Claude Context Continuity? +

Register the MCP Claude Context 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 MCP Claude Context Continuity tool call.

Deterministic rules across all 8 MCP Claude Context Continuity tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP CLAUDE CONTEXT CONTINUITY →

Instant setup, no code required.

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