List tables in the SeaTable base with their columns (name, type, key). Includes select options and link configuration where applicable.

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 a row by ID from a table

Add a single row. For multiple rows, always use append_rows instead of calling add_row in a loop. Link and file/image columns cannot be set here — use link_rows and upload_file instead.

Batch insert rows. Rejects unknown columns. Link and file/image columns cannot be set here — use link_rows and upload_file instead. Note: the response may contain column keys instead of column names due to a SeaTable API limitation.

Batch update rows. Rejects unknown columns. Link and file/image columns cannot be modified here — use link_rows/unlink_rows and upload_file instead.

Delete one or more rows from a table by their IDs.

Find 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 rows with a filter object

Batch 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.

Create 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.

Remove links between rows via the dedicated links endpoint. This is the ONLY way to remove links — link columns cannot be modified via update_rows.

Returns the normalized schema for the base

Execute SQL queries against SeaTable (SELECT, UPDATE, DELETE, INSERT). Use ? placeholders for parameters.

Syntax rules:

• Quote table/column names with backticks: Table Name, Column Name (not double quotes). Required for names with spaces, hyphens, or names matching function names.

• SELECT returns max 100 rows by default. Use LIMIT to get more (up to 10,000).

• Aliases (AS) can be used in GROUP BY, HAVING, ORDER BY — but NOT in WHERE.

• ORDER BY columns must appear in the SELECT field list.

• No JOIN keyword. Use implicit joins: FROM T1, T2 WHERE T1.col = T2.col. Only inner joins are supported.

• No subqueries, no UNION/UNION ALL.

• Empty strings are treated as NULL. Use IS NULL / IS NOT NULL instead of = "".

• Use ILIKE for case-insensitive matching (LIKE is case-sensitive).

• For multi-select/collaborator columns use: HAS ANY OF, HAS ALL OF, HAS NONE OF, IS EXACTLY (values in parentheses like IN).

UPDATE limitations:

• SET only accepts literal values (strings, numbers, booleans). No functions (date(), now(), upper()…) and no expressions (Amount + 10) allowed.

• Columns not updatable via SQL: image, file, formula, link, link-formula, geolocation, auto-number, digital-sign, button.

INSERT only works with Big Data storage enabled (Enterprise). For non-archived tables, use append_rows instead.

If a query fails, do not retry with similar syntax. Switch to an alternative tool (e.g. update_rows, find_rows) instead.

List users who have access to this base. Returns email (internal user ID) and display name. Use the email values when writing to collaborator columns. Call this once to resolve @auth.local addresses in collaborator columns before displaying them to the user.

Upload 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.

Read the content of a file attached to a row in a file or image column. Use get_row first to see available files in the column, then pass the exact file_name to select a specific file.

Returns JSON with: file_name, file_size (bytes), content, content_type, and download_link (only when content_type is "binary_url").

content_type values:

• "text": file content returned as text (.txt, .csv, .md, .json, .xml, .html, .yaml, .sql, and common programming languages)

• "pdf_text": extracted text from PDF files

• "binary_url": non-text files, files >1 MB, or external URLs — content contains a message, download_link contains the URL

Create a snapshot of the current base. Requires at least one change since the last snapshot and at least 10 minutes since the last snapshot.

Get the change history of a specific row. Returns a list of activities showing who changed what and when, including old and new values. 25 activities per page.

Add new options to a single-select or multi-select column. Use this before writing rows with option values that do not exist yet.

Health check that verifies connectivity and auth to SeaTable