SeaTable

This MCP server connects AI agents to https://cloud.seatable.io.

CommunityOnlineAPI key requiredGlobalFreeCan modify data

What it can do

  • List Tables: List tables in the SeaTable base
  • List Rows: List rows from a table with pagination (defaults: page=1, page_size=100). Use find_rows for filtering/sorting or query_sql for SQL queries.
  • Get Row: Get a row by ID from a table

What data it sees

Do you need an account

An API key from the service settings is required

This MCP server connects AI agents to https://cloud.seatable.io. Read, write, search, and link rows, run SQL queries, batch upsert data, and manage file attachments and select options. Generate an API token in your base settings to get started.

For self-hosted SeaTable servers, use the npm package — see https://github.com/seatable/seatable-mcp for setup instructions.

How to connect

How to connect SeaTable to Claude

The server address to paste into Claude settings:

https://seatable-mcp--seatable.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect SeaTable to ChatGPT

The server address to paste into ChatGPT settings:

https://seatable-mcp--seatable.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect SeaTable to Cursor

The server address to paste into Cursor settings:

https://seatable-mcp--seatable.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (18)

Raw names from tools/list. Only developers need these.

list_tablesList tables in the SeaTable base
list_rowsList rows from a table with pagination (defaults: page=1, page_size=100). Use find_rows for filtering/sorting or query_sql for SQL queries.
get_rowGet a row by ID from a table
add_rowAdd a new row to a table. Link and file/image columns cannot be set here — use link_rows and upload_file instead.
append_rowsBatch insert rows. Rejects unknown columns. Link and file/image columns cannot be set here — use link_rows and upload_file instead.
update_rowsBatch update rows. Rejects unknown columns. Link and file/image columns cannot be modified here — use link_rows/unlink_rows and upload_file instead.
delete_rowsDelete one or more rows from a table by their IDs.
find_rowsFind rows using a predicate DSL. Filtering is performed client-side. where format: {"eq":{"field":"Name","value":"foo"}} or shorthand {"Name":"foo"}. Operators: eq, ne, in, gt, gte, lt, lte, contains, starts_with, ends_with, is_null. Combine with {"and":[...]} or {"or":[...]}. Negate with {"not":{...}}.
search_rowsSearch rows with a filter object
upsert_rowsBatch upsert rows by matching on one or more key columns. If a match exists, update it; otherwise insert a new row. Rejects unknown columns. Link and file/image columns cannot be set here — use link_rows/unlink_rows and upload_file instead.
link_rowsCreate links between rows via the dedicated links endpoint. This is the ONLY way to create links — link columns cannot be written via add_row or update_rows.
unlink_rowsRemove links between rows via the dedicated links endpoint. This is the ONLY way to remove links — link columns cannot be modified via update_rows.
get_schemaReturns the normalized schema for the base
query_sqlExecute raw SQL queries against SeaTable. Supports SELECT, INSERT, UPDATE, DELETE. Use ? placeholders for parameters to prevent SQL injection.
list_collaboratorsList users who have access to this base. Returns email (internal user ID) and display name. Use the email values when writing to collaborator columns.
upload_fileUpload a file or image to a row. Accepts base64-encoded file data and attaches it to the specified file or image column. By default appends to existing files; set replace=true to overwrite.
add_select_optionsAdd new options to a single-select or multi-select column. Use this before writing rows with option values that do not exist yet.
ping_seatableHealth check that verifies connectivity and auth to SeaTable