chatlab-mcp

chatlab-mcp

Enables AI assistants to query local ChatLab chat history using natural language, with tools for session listing, message retrieval, and analytics.

Category
访问服务器

README

chatlab-mcp

English | 简体中文 | 繁體中文 | 日本語

MCP server that connects ChatLab to AI assistants (Claude Desktop, Cursor, custom agents). Query your local chat history with natural language.

Tracks ChatLab v0.19.0

Requirements

  • ChatLab installed and running
  • API enabled in ChatLab Settings → API, with a token generated
  • Node.js 18+

Installation

npx (recommended)

No installation needed. Configure your AI client directly:

{
  "mcpServers": {
    "chatlab": {
      "command": "npx",
      "args": ["-y", "chatlab-mcp"],
      "env": {
        "CHATLAB_TOKEN": "clb_xxxxxxxxxxxx",
        "CHATLAB_URL": "http://127.0.0.1:5200"
      }
    }
  }
}

From source

git clone https://github.com/gamesme/chatlab-mcp
cd chatlab-mcp
npm install && npm run build

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

With npx:

{
  "mcpServers": {
    "chatlab": {
      "command": "npx",
      "args": ["-y", "chatlab-mcp"],
      "env": {
        "CHATLAB_TOKEN": "clb_xxxxxxxxxxxx",
        "CHATLAB_URL": "http://127.0.0.1:5200"
      }
    }
  }
}

From source (use your Homebrew node to avoid version issues):

{
  "mcpServers": {
    "chatlab": {
      "command": "/opt/homebrew/bin/node",
      "args": ["/absolute/path/to/chatlab-mcp/dist/index.js"],
      "env": {
        "CHATLAB_TOKEN": "clb_xxxxxxxxxxxx",
        "CHATLAB_URL": "http://127.0.0.1:5200"
      }
    }
  }
}

Restart Claude Desktop after saving. The chatlab tools will appear in the tools list.

Tools

Core (6)

Tool Description
list_sessions List all imported chat sessions with name, platform, and message count
get_session Get details of a single session by ID
get_messages Retrieve messages with filters: keyword, time range, sender, pagination (max 100/call)
get_members List all members in a session with their platformId and message count
get_stats_overview Statistical overview: message counts, member activity, type distribution, time range
execute_sql Run aggregation queries (COUNT/GROUP BY) against the session database

Analytics (v0.19.0+, 9)

Tool Description
get_message_context N messages before/after one or more target message IDs
get_conversation_between Interleaved messages between two specific members (numeric IDs)
get_session_summaries AI-generated chat sub-session summaries (from the chat_session table)
deep_search_messages FTS5 keyword search with surrounding context window
get_time_stats Hourly / weekday / daily distribution, timezone-aware
get_member_activity Top-N members by message count with percentage of total
get_member_name_history Historical account name / nickname entries for a member
get_response_time_analysis Reply intervals between sender pairs (LAG window function)
keyword_frequency Stub — returns guidance (NLP segmentation not bundled in MCP)

Notes

  • get_messages returns at most 100 messages per call. Use the page parameter to paginate. Responses include has_more and a hint when more results exist.
  • execute_sql is for statistical aggregation only. Use get_messages or get_message_context to read message content.
  • Analytics tools issue their own SQL through the same /sql endpoint (no 200-row LIMIT injection).
  • All avatar/binary fields are stripped from responses to minimize context usage.

CLI Options

node dist/index.js --token <token> --url <url>
# or via env vars
CHATLAB_TOKEN=clb_xxx CHATLAB_URL=http://127.0.0.1:5200 node dist/index.js

CHATLAB_URL defaults to http://127.0.0.1:5200.

Development

npm test             # run all tests
npm run test:watch   # watch mode
npm run dev          # run with ts-node (no build step)
npm run build        # compile TypeScript → dist/

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选