lark-lite-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@lark-lite-mcpfetch record 'rec123' from table 'Table1'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
lark-lite-mcp
一个面向 AI Agent 的轻量飞书多维表格(Bitable)MCP。它通过飞书官方 Node.js SDK 访问数据,并在 MCP 工具与飞书 SDK 之间提供稳定的兼容层。
设计目标
通用:不绑定学者库或其他业务项目。
安全:默认只读,凭证只从进程环境变量读取。
完整:查询显式返回分页状态,可受控拉取多页。
稳定:Agent 只依赖本项目定义的返回结构,不依赖飞书原始响应字段。
可升级:飞书 SDK 与 MCP SDK 使用精确版本,由测试验证后再升级。
当前只支持飞书多维表格,不支持飞书文档、消息、日历等其他能力。
Related MCP server: Feishu MCP Server
安装与配置
生产或团队环境建议固定具体版本,避免启动时自动获取不兼容的新版本:
{
"mcpServers": {
"lark-bitable": {
"command": "npx",
"args": ["-y", "lark-lite-mcp@2.0.1"],
"env": {
"LARK_APP_ID": "cli_xxx",
"LARK_APP_SECRET": "xxx",
"LARK_READ_ONLY": "true",
"LARK_ALLOWED_BASE_TOKENS": "bascnAllowedBase",
"LARK_ALLOWED_TABLE_IDS": "tblAllowedOne,tblAllowedTwo"
}
}
}
}也可以从源码运行:
{
"mcpServers": {
"lark-bitable": {
"command": "node",
"args": ["/absolute/path/to/lark-lite-mcp/index.js"],
"env": {
"LARK_APP_ID": "cli_xxx",
"LARK_APP_SECRET": "xxx"
}
}
}
}应用仍需在飞书开放平台申请相应权限,并加入目标多维表格的协作者。
环境变量
变量 | 默认值 | 说明 |
| 必填 | 飞书自建应用 App ID |
| 必填 | 飞书自建应用 App Secret |
|
| 为 |
| 空 | 逗号分隔;为空时依赖飞书应用自身权限 |
| 空 | 逗号分隔;为空时依赖飞书应用自身权限 |
|
| 429、408 和 5xx 传输错误的最大重试次数 |
|
| 指数退避的初始等待时间 |
|
| 单次飞书 HTTP 请求超时毫秒数 |
|
|
|
不要在对话或 MCP 工具参数中提供 App Secret。Secret 只应存在于 MCP 进程环境变量或密钥管理系统中。
MCP 工具
工具 | 说明 |
| 从普通 Base URL 提取坐标,或将 |
| 分页列出 Base 中的数据表 |
| 查询单条记录 |
| 分页搜索记录;支持有上限的 |
| 更新单条记录,仅在写模式下暴露 |
分页结果使用稳定结构:
{
"items": [],
"hasMore": false,
"nextPageToken": null,
"requestId": null
}当 fetchAll=true 且命中安全上限时,结果额外返回 "truncated": true。调用方必须把它视为不完整结果。
兼容性策略
飞书原始响应只允许在 src/bitable-adapter.js 中处理。MCP 工具不直接读取 res.data.items、record_id 或 page_token 等飞书字段。SDK 或 OpenAPI 返回结构变化时,应只修改 Adapter,并保持工具返回结构不变。
依赖升级流程:
修改精确依赖版本。
运行离线单元与契约测试。
使用专用测试 Base 运行在线冒烟测试。
确认 MCP 客户端连接和工具列表。
按语义化版本发布,并在生产配置中显式升级版本。
不建议直接使用 ^ 或 latest 自动追踪飞书 SDK、MCP SDK 或本 MCP 的新版本。
开发与验证
npm install
npm test
npm run check在线冒烟测试只访问专用测试 Base:
LARK_APP_ID=cli_xxx \
LARK_APP_SECRET=xxx \
LARK_SMOKE_BASE_TOKEN=bascnTestBase \
npm run smoke在线冒烟测试不应使用生产表,也不应把凭证提交到仓库。
License
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted Airtable MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Hosted Notion MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
MCP-native open-source Notion alternative: read & write pages, databases and kanban boards.
ParseHub.dev is a hosted document-to-records service with a remote MCP server. Agents can upload a CSV, PDF, or Word file, summarize and analyze CSV data (filter, sort, group_by, and more), read text from PDF and Word files, extract attendees, agenda items, and action items from meeting notes, ask a question about an uploaded document, and store files as database records to list and read later. Each account sees only its own files and records. **Endpoint:** `https://parsehub.dev/mcp` (Streamable HTTP, stateless) **Auth:** API key in the `X-API-Key` header (keys start with `mcp_`), or `Authorization: Bearer <API key or JWT>`. Every request without credentials returns 401. **Plans:** Free (100 API requests/month, 1 document upload), or 5,000 requests/month on the $9/month or $42/year plan. Every MCP request counts toward the allowance. **Tools:** upload_csv, summarize_csv, analyze_csv, upload_document, read_document, extract_meeting_notes, ask_document, database_status, list_database_documents, get_database_document, store_document, extract_stored_meeting_notes, export_database (administrators only). Not affiliated with ParseHub (parsehub.com), the web-scraping tool. ParseHub.dev does not scrape websites. By Poietes LLC. Docs: https://parsehub.dev/guide#connect-via-mcp
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP-based service that enables AI models to seamlessly interact with Feishu (Lark) platform, supporting document reading and chatbot messaging capabilities.4 npm53MIT
- AlicenseAqualityNot gradedmaintenanceEnables interaction with Feishu (Lark) multidimensional tables (Bitable) through MCP tools, supporting operations like creating/updating/querying records, batch operations, and application management with automatic token refresh.9MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for Feishu/Lark API integration, enabling AI agents to send messages, manage groups, create and edit documents and spreadsheets, and search knowledge bases.MIT
- AlicenseNot gradedqualityDmaintenanceEnables interacting with Feishu (Lark) multidimensional tables through MCP tools. Supports listing tables, reading records, searching records and apps, and getting views.180 npmMIT