An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Baserow to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage complex data structures using only natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 9 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-03

3 capabilities in this set.

Part of 9 available through Baserow.

  1. 01

    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

  2. 02

    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

  3. 03

    List workspaces

    List all Baserow workspaces

Capability set02 / 03

04-06

3 capabilities in this set.

Part of 9 available through Baserow.

  1. 04

    Delete row

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

  2. 05

    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

  3. 06

    List applications

    List all Baserow applications (databases)

Capability set03 / 03

07-09

3 capabilities in this set.

Part of 9 available through Baserow.

  1. 07

    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

  2. 08

    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

  3. 09

    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

Real work

What teams actually run

01

Tracking Project Status

Ask your agent to list all tasks in the 'Projects' table that are assigned to Bob and are due this week. It runs the query and gives you a clean list.

02

Onboarding New Users

A developer can ask the agent to create a new row in the 'Team Members' table with a user's name, role, and start date, completing the setup instantly.

03

Auditing Data Changes

You can ask the agent to get the details of a specific row using its ID, allowing you to verify exactly what data was stored or changed.

04

Schema Review

Before writing code, ask the agent to list the fields in a table. It returns the field names and their data types, helping you plan your data structure.

Automate a task

Put Baserow to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Baserow works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Baserow to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

871ms average. Fast in production.

Baserow is checked daily against the live service.

Daily averagePeak 1118ms
Oct 3Today
Fastest day
749ms
Slowest day
1118ms
14-day trend
Stable+4%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 9 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Baserow, so you can see the experience inside your AI.

It does not authenticate your account with Baserow. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Baserow Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_Z34lWZ5owpWDpmV3OREMbmzFWjwcpZS743KcVKV7/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Baserow capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "baserow-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_Z34lWZ5owpWDpmV3OREMbmzFWjwcpZS743KcVKV7/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Baserow in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Baserow owners hand off.

This MCP is built for teams that rely on structured data but don't want to write complex API calls. Product teams can quickly query project data, developers can programmatically manage content, and data analysts can explore schemas and run advanced queries without leaving their AI client.

  • 01

    Product Teams

    Use the AI to query project tracking databases and update task statuses across multiple records.

  • 02

    Developers

    Use the AI to discover table schemas and create records programmatically, treating the database like a simple API endpoint.

  • 03

    Data Analysts

    Use the AI to explore data schemas and run filtered queries, exporting raw row data for deeper analysis.

FAQ

Questions Baserow owners ask.

  • 01

    Does this MCP let me see what data is in my databases?

    Yes. You can use capabilities like list_tables and list_rows to view the structure and content of your data. The agent can run filtered queries to pull specific sets of records for you.

  • 02

    Can I update or delete data using this connector?

    Absolutely. The MCP provides capabilities to update_row and delete_row. You just need to provide the table ID and the specific row ID, and the agent handles the modification or deletion.

  • 03

    What kind of data types can I handle?

    The schema exploration capabilities list various types, including text, number, boolean, date, select, and file. This means your agent can handle most standard no-code database data types.

  • 04

    Is this connector only for reading data?

    No. It supports full CRUD operations. You can list, get, create, update, and delete records, making it a comprehensive data management capability.

  • 05

    Do I need to write API calls to use this MCP?

    No. The entire point is that your AI agent handles the API calls for you. You just talk to it naturally, and it executes the necessary actions.

  • 06

    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.

  • 07

    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.

  • 08

    Can I filter rows by field values?

    Yes! The list_rows capability 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.

  • 09

    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.

  • 10

    How do I find my Baserow Database Token?

    Log in to your account, navigate to Settings > Database Tokens, and create a new token with appropriate workspace permissions.

  • 11

    Can I search for records via AI?

    Yes! The search_rows capability allows your agent to find records across a specific table matching your search criteria programmatically.

  • 12

    How do I find Table and Database IDs?

    Use the list_applications capability to find Database IDs, and list_database_tables to find Table IDs within a specific application.

Explore

More in Databases

Suggestions

Connect Baserow to Claude, Cursor, ChatGPT & more