// SCAN REPORT

ClaudeHistoryMCP

9 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 11 Jun 2026

1 can modify or destroy data

8 read-only

9 tools total

Community server · catalogue entry verified 11/06/2026

How to control ClaudeHistoryMCP ↓

TOOL MAP

What ClaudeHistoryMCP exposes to your agents

Read (8) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous ClaudeHistoryMCP tools

Write · Medium cloud_sync_push This tool falls under Write because it creates or uploads data to a cloud backend.

1 of ClaudeHistoryMCP's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control ClaudeHistoryMCP

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

Rate limit write operations

{
  "cloud_sync_push": {
    "limits": [
      {
        "counter": "cloud_sync_push_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "cloud_sync_pull": {
    "limits": [
      {
        "counter": "cloud_sync_pull_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 ClaudeHistoryMCP — 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 CLAUDEHISTORYMCP →

Free to start. No card required.

FULL CATALOGUE

All 9 ClaudeHistoryMCP tools

WRITE 1 tools

Write cloud_sync_push Push local knowledge entries and session summaries to the cloud server. Only pushes entries newer than the las

READ 8 tools

Read cloud_sync_pull Pull knowledge entries and session summaries from the cloud server. Merges with local data without duplicates. Read cloud_sync_status Check cloud sync configuration and connection status. Shows whether sync is configured, last sync times, and c Read find_patterns Discover recurring patterns in conversation history: common topics, frequent workflows, repeated issues. Read find_solutions Search past conversations for solutions to errors or problems. Prioritizes results containing fix/resolution l Read get_project_context Get comprehensive context for a project: recent sessions, key topics, common tools, and patterns. Useful for s Read get_session_summary Get a structured summary of a conversation session. Provide either a session ID or project name (returns most Read list_projects List all projects that have Claude Code conversation history, with session counts and activity dates. Read search_history Search past Claude Code conversations. Supports filter syntax: project:name, before:date, after:date, tool:nam

FAQ

Questions about ClaudeHistoryMCP

How do I prevent bulk modifications through ClaudeHistoryMCP? +

The ClaudeHistoryMCP server has 1 write tools including cloud_sync_push. 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 ClaudeHistoryMCP.

How many tools does the ClaudeHistory MCP server expose? +

9 tools across 2 categories: Read, Write. 8 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on ClaudeHistoryMCP? +

Register the ClaudeHistory 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 ClaudeHistoryMCP tool call.

Deterministic rules across all 9 ClaudeHistoryMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLAUDEHISTORYMCP →

Free to start. No card required.

9 ClaudeHistoryMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.