SeaTable MCP
The official Model Context Protocol (MCP) server for SeaTable, built and maintained by SeaTable GmbH. It lets AI agents interact with data in your bases — reading, writing, searching, linking, and querying rows through a focused set of tools. The server intentionally focuses on data operations, not schema management (creating/deleting tables or columns), keeping the tool set lean and safe for auto
README
SeaTable MCP
The official Model Context Protocol (MCP) server for SeaTable, built and maintained by SeaTable GmbH. It lets AI agents interact with data in your bases — reading, writing, searching, linking, and querying rows through a focused set of tools. The server intentionally focuses on data operations, not schema management (creating/deleting tables or columns), keeping the tool set lean and safe for autonomous agent use.
Quick Start
The fastest way to get started depends on your setup:
- SeaTable Cloud — Use the hosted MCP server at
mcp.seatable.com, no installation needed - Self-hosted SeaTable — Run the MCP server locally via
npxin your IDE
SeaTable Cloud (hosted MCP server)
If you use SeaTable Cloud, there is a hosted MCP server ready to use — no installation required. Configure your MCP client with the Streamable HTTP endpoint:
Claude Desktop — add to claude_desktop_config.json:
{
"mcpServers": {
"seatable": {
"type": "streamable-http",
"url": "https://mcp.seatable.com/mcp",
"headers": {
"Authorization": "Bearer your-api-token"
}
}
}
}
Cursor / VSCode — add to your MCP settings (JSON):
{
"mcp.servers": {
"seatable": {
"type": "streamable-http",
"url": "https://mcp.seatable.com/mcp",
"headers": {
"Authorization": "Bearer your-api-token"
}
}
}
}
Self-hosted SeaTable
For self-hosted SeaTable instances, run the MCP server locally via npx. Your IDE starts and manages the process automatically.
Claude Desktop — add to claude_desktop_config.json:
{
"mcpServers": {
"seatable": {
"command": "npx",
"args": ["-y", "@seatable/mcp-seatable"],
"env": {
"SEATABLE_SERVER_URL": "https://your-seatable-server.com",
"SEATABLE_API_TOKEN": "your-api-token"
}
}
}
}
Cursor / VSCode — add to your MCP settings (JSON):
{
"mcp.servers": {
"seatable": {
"command": "npx",
"args": ["-y", "@seatable/mcp-seatable"],
"env": {
"SEATABLE_SERVER_URL": "https://your-seatable-server.com",
"SEATABLE_API_TOKEN": "your-api-token"
}
}
}
}
Deployment Options
If you need to run your own server instance — for example on your own infrastructure, with multi-base support, or in multi-tenant mode — use one of the options below.
HTTP Server (Network Access)
Run a local HTTP server with Streamable HTTP transport:
PORT=3001 npx -y @seatable/mcp-seatable --sse
# Health check
curl http://localhost:3001/health
# MCP endpoint: POST/GET/DELETE http://localhost:3001/mcp
Multi-Base (Selfhosted)
Serve multiple bases from a single process:
SEATABLE_SERVER_URL=https://your-seatable-server.com \
SEATABLE_BASES='[{"base_name":"CRM","api_token":"token_abc"},{"base_name":"Projects","api_token":"token_def"}]' \
npx -y @seatable/mcp-seatable
Each tool automatically gets a base parameter. Use list_bases to see available bases.
Managed Mode (Multi-Tenant HTTP)
For hosting an MCP endpoint where each client authenticates with their own SeaTable API token:
SEATABLE_MODE=managed \
SEATABLE_SERVER_URL=https://your-seatable-server.com \
PORT=3000 npx -y @seatable/mcp-seatable --sse
Clients pass their API token via Authorization: Bearer <token> on session initialization. The server validates the token against SeaTable and applies rate limits (60 req/min per token, 120/min per IP, 5 concurrent connections per token).
Docker
docker run -d --name seatable-mcp \
-p 3000:3000 \
-e SEATABLE_SERVER_URL=https://your-seatable-server.com \
-e SEATABLE_API_TOKEN=your-api-token \
seatable/seatable-mcp:latest
# Health check
curl http://localhost:3000/health
Security Model
The security characteristics differ significantly between transport modes:
| stdio (default) | Selfhosted HTTP | Managed HTTP | |
|---|---|---|---|
| Network exposure | None (local process) | TCP port, no auth | TCP port, Bearer auth |
| Authentication | Not needed (local) | None | Per-session token validated against SeaTable |
| Rate limiting | None | None | Per-token, per-IP, global |
| Connection limits | N/A | None | 5 concurrent sessions per token |
| Data scope | All configured bases | All configured bases | One base per client token |
⚠️ Warning: Selfhosted HTTP mode (
--sse/--http) has no authentication. Anyone who can reach the port gets full access to all configured bases, including write and delete operations. Only run it in trusted networks (localhost, Docker-internal) or behind a reverse proxy that handles authentication. For untrusted networks, use managed mode instead.
Environment Variables
Required:
SEATABLE_SERVER_URL— Your SeaTable server URL
Authentication (one of these is required in selfhosted mode):
SEATABLE_API_TOKEN— Single-base API tokenSEATABLE_BASES— Multi-base: JSON array (e.g.'[{"base_name":"CRM","api_token":"..."}]')
Optional:
SEATABLE_MODE—selfhosted(default) ormanaged(multi-tenant HTTP with per-client auth)SEATABLE_MOCK=true— Enable mock mode for offline testingMETRICS_PORT— Prometheus metrics port (default:9090, HTTP mode only)
Monitoring
In HTTP mode, the server exposes Prometheus metrics on a separate port (default 9090):
curl http://localhost:9090/metrics
Available metrics:
| Metric | Type | Description |
|---|---|---|
mcp_tool_calls_total{tool, status} |
Counter | Tool calls by name and result (success/error) |
mcp_tool_calls_by_tool_total{tool} |
Counter | Total calls per tool (regardless of outcome) |
mcp_tool_duration_seconds{tool} |
Histogram | Tool execution time |
mcp_http_requests_total{method, status} |
Counter | HTTP requests by method and status code |
mcp_rate_limit_exceeded_total{type} |
Counter | Rate limit rejections (global/per_ip/per_token) |
mcp_auth_validations_total{result} |
Counter | Auth validations (success/failure/cache_hit) |
mcp_active_sessions |
Gauge | Currently active HTTP sessions |
mcp_active_connections |
Gauge | Currently active connections |
seatable_api_requests_total{operation, status} |
Counter | SeaTable API calls by operation |
seatable_api_duration_seconds{operation} |
Histogram | SeaTable API latency |
Plus standard Node.js metrics (memory, CPU, event loop) via prom-client.
The metrics server only starts in HTTP mode (not stdio) and binds to 0.0.0.0 — in Docker, expose the port only within your internal network.
MCP Tools
Schema Introspection
list_tables— Get all tables with metadataget_schema— Get complete database structurelist_bases— List available bases (multi-base mode only)list_collaborators— List users with access to the base (for collaborator columns)
Reading Data
list_rows— Paginated row listing with sortingget_row— Retrieve specific row by IDfind_rows— Client-side filtering with DSLsearch_rows— Search via SQL WHERE clausesquery_sql— Execute SQL queries with parameterized inputs
Writing Data
add_row— Add single new rowappend_rows— Batch insert rowsupdate_rows— Batch update rowsupsert_rows— Insert or update rows by key columnsdelete_rows— Remove rows by IDupload_file— Upload a file or image to a row (base64-encoded)
Linking
link_rows— Create relationships between rowsunlink_rows— Remove relationships between rows
Utilities
add_select_options— Add new options to single-select or multi-select columnsping_seatable— Health check with latency monitoring
Supported Column Types
SeaTable bases can contain many different column types. The following table shows which types can be written via the API and what format to use.
| Column Type | Writable | Value Format |
|---|---|---|
| Text | Yes | "string" |
| Long Text | Yes | "Markdown string" |
| Number (incl. percent, currency) | Yes | 123.45 |
| Checkbox | Yes | true / false |
| Date | Yes | "YYYY-MM-DD" or "YYYY-MM-DD HH:mm" |
| Duration | Yes | "h:mm" or "h:mm:ss" |
| Single Select | Yes | "option name" |
| Multiple Select | Yes | ["option a", "option b"] |
| Yes | "user@example.com" |
|
| URL | Yes | "https://..." |
| Rating | Yes | 4 (integer) |
| Geolocation | Yes | {"lat": 52.52, "lng": 13.40} |
| Collaborator | Yes | ["0b995819003140ed8e9efe05e817b000@auth.local"] — use list_collaborators to get user IDs |
| Link | Yes | Use link_rows / unlink_rows tools |
| Image / File | Yes | Use upload_file tool with base64-encoded data |
| Formula / Link Formula | No | Read-only, computed by SeaTable |
| Creator / Created Time / Modified Time | No | Read-only, set automatically |
| Auto Number | No | Read-only, set automatically |
| Button / Digital Signature | No | Not accessible via API |
Tool Examples
// List all tables
{ "tool": "list_tables", "args": {} }
// Get rows with pagination
{ "tool": "list_rows", "args": { "table": "Tasks", "page_size": 10, "order_by": "_ctime", "direction": "desc" } }
// Add rows
{ "tool": "append_rows", "args": { "table": "Tasks", "rows": [{ "Title": "New Task", "Status": "Todo" }] } }
// SQL query
{ "tool": "query_sql", "args": { "sql": "SELECT Status, COUNT(*) as count FROM Tasks GROUP BY Status" } }
Programmatic Usage
import { createMcpServer } from '@seatable/mcp-seatable'
const server = await createMcpServer({
serverUrl: 'https://your-seatable-server.com',
apiToken: 'your-api-token',
})
Mock Mode
SEATABLE_MOCK=true npm run dev
In-memory tables and rows for demos and tests without a live SeaTable instance.
Development
Prerequisites
- Node.js >= 18
Setup
git clone https://github.com/seatable/seatable-mcp
cd seatable-mcp
npm install
cp .env.example .env # Configure your SeaTable settings
npm run dev # Start in watch mode
Scripts
npm run dev— Start server in watch mode (tsx)npm run build— Compile TypeScriptnpm run start— Run compiled servernpm test— Run tests (vitest)npm run lint— Lint codenpm run typecheck— TypeScript type check
Testing Tools
node scripts/mcp-call.cjs ping_seatable '{}'
node scripts/mcp-call.cjs list_tables '{}'
node scripts/mcp-call.cjs list_rows '{"table": "Tasks", "page_size": 5}'
Troubleshooting
| Issue | Solution |
|---|---|
Invalid API token |
Check SEATABLE_API_TOKEN |
Base not found |
Check API token permissions |
Connection timeout |
Check SEATABLE_SERVER_URL and network access |
Permission denied |
Ensure API token has required base permissions |
You don't have permission to perform this operation on this base. |
API token is read-only or row limit exceeded |
Asset quota exceeded. |
Storage quota reached — delete files or upgrade plan |
too many requests |
Rate-limited by SeaTable — requests are automatically retried with backoff (3 attempts) |
License
MIT
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。