How do I get a Baserow API Token?

Log in to your Baserow workspace, go to **Database Settings > API Tokens** (or Workspace Settings > API Tokens), click **Create Token**, give it a name and set the permissions (create, read, update, delete) for specific tables. Copy the token immediately — it won't be shown again.

Can I create and update rows programmatically?

Yes! Use `create_row` with the table ID and a JSON object of field_name: value pairs. Use `update_row` with the table ID, row ID and the fields to update. First use `list_fields` to discover the available field names and their types for the table.

Can I filter rows by field values?

Yes! The `list_rows` tool supports pagination and ordering. Use the `page` and `size` parameters for pagination, and `order_by` to sort by any field (prefix with `-` for descending). The underlying API also supports field-level filtering through the filter parameter.

What field types does Baserow support?

Baserow supports: text, number, boolean, date, long_text, email, url, single_select, multiple_select, link_row (relationships), file, rating, formula, lookup, rollup, last_modified and created_on fields. Use `list_fields` to see the exact types in your table.

Baserow MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Baserow
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Baserow through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Baserow Assistant",
            instructions=(
                "You help users interact with Baserow. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Baserow"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Baserow MCP Server

Connect your Baserow databases to any AI agent and take full control of your data through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Baserow through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Baserow, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Database Discovery — List all databases and tables the token has access to with their schemas
Schema Exploration — Browse table fields (columns) with their types (text, number, boolean, date, select, etc.)
Row Operations — List, create, update and delete rows with full CRUD support
Filtered Queries — Query rows with pagination, ordering and field-based filtering
View Management — List configured views (grid, gallery, kanban, form, calendar) with their filter and sort rules

The Baserow MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Baserow to OpenAI Agents SDK via MCP

Follow these steps to integrate the Baserow MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Baserow

Why Use OpenAI Agents SDK with the Baserow MCP Server

OpenAI Agents SDK provides unique advantages when paired with Baserow through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Baserow + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Baserow MCP Server delivers measurable value.

Automated workflows: build agents that query Baserow, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Baserow, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Baserow tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Baserow to resolve tickets, look up records, and update statuses without human intervention

Baserow MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Baserow to OpenAI Agents SDK via MCP:

create_row

Requires the table ID and a JSON object with field_name: value pairs matching the table schema. Use list_fields to discover available field names. Returns the created row with its ID and all field values. Create a new row in a Baserow table

delete_row

Provide the table ID and row ID. WARNING: this action is irreversible. Delete a row from a Baserow table

get_row

Field names are returned in user-readable format. Provide the table ID and row ID. Get a specific row from a Baserow table

get_table

Provide the table ID from list_tables. Get details for a specific Baserow table

list_databases

Each database shows its ID, name, workspace and creation date. Use this to discover available databases before querying their tables. List all Baserow databases

list_fields

Each field shows its ID, name, type (text, number, boolean, date, single_select, long_text, link_row, file, etc.), order and required status. Use this to understand the data schema before querying or creating rows. List fields (columns) of a Baserow table

list_rows

Optionally filter by field values (using user_field_names) and set page/size for pagination. Results include count, next/previous page URLs and the rows array. Use field names (not IDs) for readable results. List rows in a Baserow table

list_tables

Each table shows its ID, name, database, field count and creation date. Use this to discover the data schema before querying rows. List all tables accessible in Baserow

list_views

Each view shows its ID, name, type, filter settings and sort rules. Useful for understanding how data is organized and filtered in the UI. List views configured for a Baserow table

update_row

Requires the table ID, row ID and a JSON object with field_name: value pairs for the fields to update. Only provided fields will be modified. Use list_fields to discover available field names. Update an existing row in a Baserow table

Example Prompts for Baserow in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Baserow immediately.

"List all tables in my Baserow workspace."

"Show me all rows in the Tasks table where Status is 'In Progress'."

"Create a new task called 'Review PR #234' assigned to Alice with status 'To Do'."

Troubleshooting Baserow MCP Server with OpenAI Agents SDK

Common issues when connecting Baserow to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Baserow + OpenAI Agents SDK FAQ

Common questions about integrating Baserow MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.