Baserow connector for AI agents

Tools your data agent reaches for on Baserow, scoped per user.

CALL ANY TOOL

14 tools for database tables in Baserow: list tables and fields, search and filter rows, create, update, move, and delete rows, batch up to 200 rows at once, add fields, and upload files by URL.

baserow_batch_create_rows

Batch create rows

Create up to 200 rows in a table in one request. Returns the created rows in the same order as the request, each with its id. Use this for bulk inserts; use baserow_create_row for a single row.

Parameters

Name

Type

Required

Description

items

array

Required

List of row objects to create, from 1 to 200. Each object uses the same keys as baserow_create_row. Example: [{"Name": "Acme"}, {"Name": "Globex"}].

table_id

integer

Required

ID of the Baserow table. Get it from baserow_list_tables. Example: 1234.

before

integer

Optional

Place the new rows before the row with this id. Leave empty to add them at the end. Example: 42.

user_field_names

boolean

Optional

Set true to use field names (for example Name) as keys in the request and response. Leave empty to use Baserow's internal keys such as field_123. Use baserow_list_fields to see both.

baserow_batch_delete_rows

Batch delete rows

baserow_batch_update_rows

Batch update rows

baserow_check_token

Check token

baserow_create_field

Create field

baserow_create_row

Create row

baserow_delete_row

Delete row

baserow_get_row

Get row

baserow_list_fields

List fields

baserow_list_rows

List rows

baserow_list_tables

List tables

baserow_move_row

Move row

baserow_update_row

Update row

baserow_upload_file_via_url

Upload file via url

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Baserow tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["baserow"], toolNames: [
    "baserow_list_fields",
    "baserow_list_rows",
    "baserow_batch_update_rows"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Mark every Pipeline row closed before June as Archived" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["baserow"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Mark every Pipeline row closed before June as Archived" }],
  tools,
});

// Execute the tool call with the user's vaulted Baserow access token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["baserow"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Mark every Pipeline row closed before June as Archived" }],
  tools,
});

// Tool call runs with the user's vaulted Baserow access token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["baserow"] }, pageSize: 100,
});

const agent = new Agent({
  name: "data_agent",
  model: "gemini-2.5-pro",
  instruction: "Baserow tools scoped to this user",
  tools,
});

await agent.run("Mark every Pipeline row closed before June as Archived");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Baserow tool. Click to copy, paste into your agent, done.

Rows

Copy the prompt

Copied

List rows in the Pipeline table where Status is New.

Copy the prompt

Copied

Add a row to Pipeline for Acme with owner Priya and status Qualified.

Copy the prompt

Copied

Update row 42 in Pipeline to status Won.

Batches

Copy the prompt

Copied

Create these 25 leads as rows in the Pipeline table.

Copy the prompt

Copied

Set Status to Archived on every row closed before June.

Copy the prompt

Copied

Delete the 10 duplicate rows I listed.

Tables and fields

Copy the prompt

Copied

List every table I can access.

Copy the prompt

Copied

Show the fields and types in the Customers table.

Copy the prompt

Copied

Add a Renewal Date field to the Customers table.

SEE HOW AUTH WORKS

Each user connects their own Baserow access token once, and Scalekit sends it with every call. Access tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Baserow

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Baserow

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Baserow

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Baserow

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other database connectors.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

GTM and RevOps Teams

Deal room sync

Pulls opportunity context from Salesforce, captures key decisions from Slack, and syncs a running summary to the deal room doc in Google Drive, but only when the deal actually changed.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Baserow access token looks fine in a demo. In production every row change looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Baserow today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Baserow as the user or through a shared access token?

As the user. Each user connects their own Baserow access token once, and Scalekit sends it with every call. Audit logs attribute every row change to that user, not a shared service account.

Where is the Baserow access token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Baserow?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example baserow_list_rows and baserow_get_row without baserow_batch_delete_rows, which deletes up to 200 rows in one request. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Baserow access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Which Baserow tables can the agent reach?

The tables the user's access token can reach. baserow_list_tables returns every one of them with its id, and baserow_check_token confirms the token is still valid before the agent starts work.