mcpField
F
Feishu Business Operations

Feishu Business Operations

Local
github.com/haohanghao0321-cpuCommunication0Updated 23w ago
Repository

About Feishu Business Operations

Feishu Business Operations is an MCP server for teams managing Feishu/Lark Bitable tables and approvals. Its scenario-based tools cover table operations, AI-assisted schema design, and approval tracking and analysis.

Key features

  1. 01Search and query Bitable tables
  2. 02Batch upsert records
  3. 03Create tables and define fields
  4. 04Design schemas from descriptions with AI
  5. 05List, alert on, and analyze approvals

Use cases

  1. 01Find tables and inspect matching records
  2. 02Write batches of business records
  3. 03Draft a table schema from a business need
  4. 04Identify delayed approvals and review statistics

MCP support

The server exposes eight Feishu/Lark Bitable and approval tools to MCP clients, including search, queries, writes, creation, schema design, alerts, and statistics.

#feishu#lark#bitable#approval#mcp-server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "feishu-scenarios": {
      "command": "npx",
      "args": [
        "-y",
        "feishu-scenarios-mcp"
      ],
      "env": {
        "FEISHU_APP_ID": "<FEISHU_APP_ID>",
        "FEISHU_APP_SECRET": "<FEISHU_APP_SECRET>",
        "FEISHU_BITABLE_APP_TOKEN": "<FEISHU_BITABLE_APP_TOKEN>",
        "FEISHU_ENV": "<FEISHU_ENV>",
        "FEISHU_USER_ID": "<FEISHU_USER_ID>",
        "DEEPSEEK_API_KEY": "<DEEPSEEK_API_KEY>"
      }
    }
  }
}
Run commandnpx -y feishu-scenarios-mcp
Environment variables to set
FEISHU_APP_ID
FEISHU_APP_SECRETSecret
FEISHU_BITABLE_APP_TOKENSecret
FEISHU_ENV
FEISHU_USER_ID
DEEPSEEK_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmfeishu-scenarios-mcp

Tools

8

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
keywordstringNoTable name keyword; supports fuzzy search. Leave blank to return the first 10 tables.

Details

From the project README

feishu-scenarios-mcp

AI-native business operations MCP server for Feishu/Lark. 8 scenario-based tools covering multidimensional tables (Bitable) and approvals — search, query, write, create, AI schema design, approval tracking, alerts, and statistics.

Installation

npm install -g feishu-scenarios-mcp

Or run directly:

npx feishu-scenarios-mcp

Configuration

Create a .env file with your Feishu app credentials:

FEISHU_APP_ID=cli_xxxxxxxxxxxx
FEISHU_APP_SECRET=xxxxxxxxxxxxxxxxxxxxxxxx
FEISHU_BITABLE_APP_TOKEN=xxxxxxxxxxxx
FEISHU_ENV=feishu
VariableRequiredDescription
FEISHU_APP_IDYesFeishu app ID from Developer Console
FEISHU_APP_SECRETYesFeishu app secret
FEISHU_BITABLE_APP_TOKENFor bitableBitable app token
FEISHU_ENVNofeishu (default) or lark
FEISHU_USER_IDFor approvalYour Feishu user open_id
DEEPSEEK_API_KEYFor schema AIDeepSeek API key for AI table design

Claude Desktop Setup

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "feishu-scenarios": {
      "command": "npx",
      "args": ["-y", "feishu-scenarios-mcp"],
      "env": {
        "FEISHU_APP_ID": "cli_xxxxxxxxxxxx",
        "FEISHU_APP_SECRET": "xxxxxxxxxxxxxxxx",
        "FEISHU_BITABLE_APP_TOKEN": "xxxxxxxxxxxx",
        "FEISHU_ENV": "feishu"
      }
    }
  }
}

Tools

Bitable (多维表格)
ToolDescription
bitable_searchSearch tables by keyword. Returns table ID, name, field preview, record count.
bitable_queryQuery records with optional filters.
bitable_upsertBatch write records. Auto field-name matching and type conversion.
bitable_createCreate a new table with field definitions.
bitable_schema_aiAI-designed table schema from business description. Requires DEEPSEEK_API_KEY.
Approval (审批)
ToolDescription
approval_listQuery approval instances by status, type, applicant, time range.
approval_alertsFind bottlenecks and overtime approvals. Default threshold 48h.
approval_statsApproval statistics: by status, type, month, top applicants.

Usage Examples

Search tables:

"搜一下包含'审批'的表格"

Query records:

"查一下积压跟踪表里 pending 状态的记录"

Write records:

"往跟踪表写一条记录，负责人张三，状态待处理"

AI design table:

"帮我设计一张跟踪审批积压的表"

Approval alerts:

"谁审批最慢"

Approval statistics:

"本月审批通过率"

Feishu Bot (Mobile)

The package also includes a WebSocket-based Feishu bot for mobile access:

npx feishu-scenarios-mcp-bot

Setup guide: docs/bot-setup.md

Required Feishu Permissions

  • approval:instance — read approval instances
  • bitable:app — access bitable
  • im:message — bot messaging
  • im:message:send_as_bot — send bot messages

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.