SeaTable integration
SeaTable bases through the API Gateway: exchange an API-Token for a short lived Base-Token, read the base structure, list, read, append, update and delete rows, run SQL against a base, list views and columns, create a table, and get an upload link for attachments. Works against the hosted service and against a self-hosted SeaTable server, so the server host is part of the connection.
Say what should happen.
The workflow builds itself.
Common SeaTable use cases
- writing collected data into a SeaTable table
- checking a column type before writing a value
- discovering the table names before reading rows
- cleaning up rows a workflow has already processed
- writing a computed status back onto existing rows
- obtaining the Base-Token before any row or table call
- pulling the contents of a SeaTable table into a workflow
- preparing an attachment upload before writing a file column
- reusing an existing view filter rather than writing a query
- filtering rows on a range instead of pulling the whole table
What you can do with SeaTable
Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.
Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.
Row, 5 operations
append_rowsAppend rowsPOSTAppends rows to a table and returns the ids of the rows that were created.delete_rowsDelete rowsDELETEDeletes the listed row ids from a table.get_rowGet rowGETReturns every column of a single row identified by its row id.list_rowsList rowsGETReturns rows of a table, or only the rows and visible columns of a view.update_rowsUpdate rowsPUTUpdates the given columns on existing rows, leaving other columns untouched.
Base, 1 operation
get_metadataGet metadataGETReturns the structure of a base with every table, column and view, but no data.
Column, 1 operation
list_columnsList columnsGETReturns the columns of a table, or the visible columns of a view.
Query, 1 operation
query_sqlQuery sqlPOSTRuns SELECT, UPDATE or DELETE against a base and returns the result set.
Table, 1 operation
create_tableCreate tablePOSTCreates a table in a base and returns the updated base structure.
Token, 1 operation
get_base_tokenGet base tokenGETReturns the Base-Token and the base uuid needed by every other call here.
Upload link, 1 operation
get_upload_linkGet upload linkGETReturns the upload link and the parent and relative paths an upload needs.
View, 1 operation
list_viewsList viewsGETReturns the views of a table together with their settings.
Use SeaTable from Claude Code, Cursor or Codex
Connect SeaTable in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its SeaTable operations become tools the client can call, next to every other integration you connected.
claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"
[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"{
"mcpServers": {
"livecontext": {
"type": "http",
"url": "https://livecontext.ai/mcp",
"headers": {
"X-API-Key": "YOUR_API_KEY"
}
}
}
}How to connect SeaTable
- Create your workspace
Sign up free. Nothing to install.
- Connect SeaTable once
Add your SeaTable connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
- Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.
SeaTable integration FAQ
What can you do with the SeaTable integration?
LiveContext exposes 12 operations on SeaTable, covering row, base, column and query. Common uses include writing collected data into a SeaTable table, checking a column type before writing a value and discovering the table names before reading rows.
