广告合作
MCP.so
登录
S

Seatable MCP Server

@brianmoney

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

brianmoney

提交者

Brian Money

关于 Seatable MCP Server

A comprehensive Model Context Protocol (MCP) server for SeaTable that exposes end‑to‑end database capabilities (schema introspection, CRUD, querying, linking, select option management, and file attachment stubs) through 18+ rigorously defined tools. You can run it:

#mcp#seatable#database

Seatable MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "seatable": {
      "command": "npx",
      "args": [
        "-y",
        "@aspereo/mcp-seatable"
      ],
      "env": {
        "SEATABLE_SERVER_URL": "https://your-seatable-server.com",
        "SEATABLE_API_TOKEN": "your-api-token",
        "SEATABLE_BASE_UUID": "your-base-uuid"
      }
    }
  }
}

Seatable MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Seatable Mcp?

Seatable Mcp is a Model Context Protocol (MCP) server that provides end‑to‑end database capabilities for SeaTable, including schema introspection, CRUD operations, querying, linking, select option management, and file attachment stubs via 18+ rigorously defined tools. It can be deployed as a local CLI (stdio) server, a local HTTP SSE server, or a globally distributed Cloudflare Worker with dual transport support.

How to use Seatable Mcp?

Install and run with npx -y @aspereo/mcp-seatable, then configure environment variables (SEATABLE_SERVER_URL, SEATABLE_API_TOKEN, SEATABLE_BASE_UUID). Integrate with MCP clients (Claude Desktop, Cursor, VS Code) by adding the server configuration to their settings. For local SSE development, set PORT=3001 and use the --sse flag. For Cloudflare Workers, clone the repo, run npm install and npx wrangler deploy.

Key features of Seatable Mcp

  • Complete CRUD operations for rows and tables
  • Advanced querying with DSL and raw SQL support
  • Schema management (create, modify, delete tables/columns)
  • Safe SQL execution with parameterized queries
  • Real‑time health monitoring with connection status and latency
  • Mock mode for offline testing without a live SeaTable

Use cases of Seatable Mcp

  • Use with Claude Desktop for natural‑language database management
  • Integrate with Cursor or VS Code alongside GitHub Copilot
  • Run as a Cloudflare Worker for production, multi‑user web applications
  • Develop and test locally using the SSE server and MCP Inspector

常见问题

1

What environment variables are required?

You must set `SEATABLE_SERVER_URL`, `SEATABLE_API_TOKEN`, and `SEATABLE_BASE_UUID`. Optionally, `SEATABLE_TABLE_NAME` for a default table and `SEATABLE_MOCK=true` for offline mock mode.

2

How do I run in mock mode?

Set `SEATABLE_MOCK=true` in your environment. The server will use in‑memory mock data, useful for testing and demos without a live SeaTable.

3

How do I deploy to Cloudflare Workers?

Clone the repository, run `npm install`, then deploy with `npx wrangler deploy`. The Worker supports both SSE (`/sse`) and Streamable HTTP (`/mcp`) transports with persistent sessions via Durable Objects.

4

Is authentication required for the Cloudflare Worker?

As of v1.0.3, all tools are exposed without authentication. Do not deploy to a public URL containing sensitive data until OAuth and scoped permissions (planned) are enabled. Mitigate risk by keeping the Worker URL private or restricting access via Cloudflare Access.

5

What transports does Seatable Mcp support?

It supports three transports: stdio (for traditional CLI MCP clients), SSE (for local or remote development), and both SSE and Streamable HTTP (for Cloudflare Worker deployments). The Worker also provides a health endpoint at `/health`.

评论

其他 分类下的更多 MCP 服务器

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

广告合作