chatlab-mcp
Enables AI assistants to query local ChatLab chat history using natural language, with tools for session listing, message retrieval, and analytics.
README
chatlab-mcp
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_messagesreturns at most 100 messages per call. Use thepageparameter to paginate. Responses includehas_moreand ahintwhen more results exist.execute_sqlis for statistical aggregation only. Useget_messagesorget_message_contextto read message content.- Analytics tools issue their own SQL through the same
/sqlendpoint (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
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。