Bubble.io MCP for AI. Manage Records and Run Workflows with Chat.

Q: Can I search for records with specific filters?

Yes! Use the searchthings tool. You can provide a constraints JSON array to filter by fields (e.g., equals, greater than). You can also control the limit and sortfield to refine your results.

Q: How do I trigger a backend workflow?

Simply use the triggerworkflow tool by providing the workflowname (the URL-friendly name defined in your Bubble API settings). This allows your AI to execute complex logic defined in your Bubble backend.

Q: Is it possible to create many records at once?

Yes, the bulkcreatethings tool allows you to create up to 1,000 records in a single call. You should provide the data in NDJSON format (one JSON object per line) for high-performance data ingestion.

Q: What is the difference between using updatething versus replacething when I modify existing data?

Use updatething (Patch) when you only want to change specific fields, leaving all other data intact. If you use replacething (Put), be careful because any field you omit will reset to its default value or get cleared.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Bubble.io (No-code Application Platform API) lets your AI agent read, write, and modify data in your entire Bubble application. You can perform deep database operations—like creating thousands of records or running complex backend workflows—all using natural language commands.

What your AI can do

Bulk create things

Creates multiple data records in your Bubble database from a single request.

Create thing

Adds one new data record into the Bubble database using specific fields.

Delete thing

Permanently removes an existing data record from the Bubble database.

+ 5 more capabilities included

Manage all application data records

Create, read, update, or delete individual data entries (Things) within your Bubble database.

Query specific record details

Fetch the full metadata for any single item by its unique ID.

Perform high-volume data creation

Build hundreds of records simultaneously using a bulk operation endpoint.

Search and filter complex datasets

Find exactly what you need by applying filters, sorting rules, or pagination to large tables.

Execute business logic workflows

Trigger specific backend processes, like sending emails or processing payments, without needing manual clicks in the Bubble editor.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Bubble.io (No-code Application Platform API) - 8 Tools

These eight tools give your agent complete control over creating, reading, updating, deleting records, and running every major backend process in your Bubble application.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Bubble.io (No-code Application Platform API) on Vinkius

Bulk Create Things

Creates multiple data records in your Bubble database from a single request.

Create Thing

Adds one new data record into the Bubble database using specific fields.

Delete Thing

Permanently removes an existing data record from the Bubble database.

Get Thing

Retrieves all detailed information for a specific data record using its unique ID.

Replace Thing

Overwrites an existing data record completely, resetting any fields that aren't...

Search Things

Searches your database by applying filters, sorting rules, and handling large result sets.

Trigger Workflow

Manually starts a specific backend business process defined within Bubble.

Update Thing

Saves changes to an existing data record without overwriting all its original fields.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Bubble.io integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "bubbleio-no-code-application-platform-api": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Bubble.io tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"bubbleio-no-code-application-platform-api": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Bubble.io (No-code Application Platform API), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Bubble.io. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 8 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Managing app data used to mean jumping between tabs and running manual queries.

Today, if you need a quick report, you click into the dashboard, filter by date range, hit 'Run Report,' then copy the results. If you want to update something, you find the record, open the edit panel, change the field, and manually save it. It's clicking, searching, copying, and pasting—a cycle that kills momentum.

With this MCP connected via Vinkius, those manual steps vanish. You just tell your agent what you need: 'Show me all active users in California who haven't logged in this month.' The system handles the complex query logic of `search_things` and spits out the answer immediately.

The `trigger_workflow` tool executes backend business logic.

Before, triggering a process—like marking an order as 'Paid' and notifying accounting—required several manual steps: updating the status field, then hitting the separate notification button, and finally confirming payment details. It was fragile and prone to human error.

Now, you simply ask your agent to trigger the workflow by name. The system handles the entire sequence of logic internally; it's one command that executes multiple complex backend actions.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

You can treat your no-code app's database like a terminal window. This MCP lets your AI agent interact with the core logic and data behind your Bubble application, going way beyond simple chat inputs. Need to update 100 user records? Done. Triggering a complex payment workflow for a new customer is routine.

The system handles full CRUD operations on every exposed data type, letting you search using advanced constraints or run massive bulk updates in one go. When your agent completes these actions, it's routed through the Vinkius catalog, making sure your entire team—from developers debugging code to ops staff running maintenance routines—gets a single point of access for everything the app does.

Built · Hosted · Managed by Vinkius Bubble.io API - Manage Data & Workflows MCP

Server ID 019e5d04-457b-7032-9768-504d3a6534b7

Vinkius Inspector

Compliance Grade F

Score 3.6/100

Report View Report ↗

What Changes When You Connect

Stop clicking through multiple dashboards to get a report. Use search_things to query complex constraints, letting your agent find data across massive datasets in one chat command.

Need to onboard 50 new users? Instead of running fifty individual API calls, use bulk_create_things to inject hundreds of records into the database instantly.

When a customer needs special handling, don't manually trigger processes. Use trigger_workflow to execute complex business logic, like processing refunds or sending alerts, on demand.

Updating data shouldn't mean deleting and recreating it. With update_thing, you only send the fields that changed, preserving data integrity while making modifications.

The ability to use get_thing means your agent always knows exactly which unique ID (UID) it's talking about, preventing ambiguous or incorrect operations.

See it in action

01 01

Auditing a user account

A PM wants to see every record associated with 'Widget X' that was modified last week. They ask their agent to run a query, and the agent uses search_things to find all matching records, returning only those within the specified date range.

02 02

Processing large data imports

An ops team receives 800 new product listings that need to be entered into Bubble. Instead of running 800 separate calls, they use bulk_create_things to ingest the entire dataset in one transaction.

03 03

Automating payment failure handling

A system detects a failed payment. The agent is instructed to find the related transaction using its UID (get_thing), and then immediately uses trigger_workflow to initiate a manual investigation process for human review.

The honest tradeoffs

Overwriting necessary data

Anti-pattern

A user tries to update only the phone number, but running an API call that uses replace_thing accidentally clears out all their saved notes and address details.

The Fix

Don't use a full replacement. For targeted changes, always use update_thing. This tool allows you to send only the fields you want to change while leaving everything else intact.

Forgetting required IDs

Anti-pattern

Trying to modify an existing record without knowing its Unique ID (UID) means the operation fails, and no changes are made.

The Fix

First, you must use get_thing by providing the specific UID. This ensures your agent has the necessary context before attempting any read or write operations.

When It Fits, When It Doesn't

Use this MCP if your application's core functionality relies on structured data (records/tables) and backend logic that needs automation. Think: database, user profiles, inventory management, financial transactions. This is the right place when you need to execute CRUD operations or run defined workflows via chat.

Don't use this if all you need to do is send a simple message or retrieve an unstructured document. If your goal is simply messaging, use a dedicated communication MCP instead. Only reach for data manipulation tools like bulk_create_things when the records themselves are the point of failure or success.

Questions you might have

Can I search for records with specific filters? +

Yes! Use the search_things tool. You can provide a constraints JSON array to filter by fields (e.g., equals, greater than). You can also control the limit and sort_field to refine your results.

How do I trigger a backend workflow? +

Simply use the trigger_workflow tool by providing the workflow_name (the URL-friendly name defined in your Bubble API settings). This allows your AI to execute complex logic defined in your Bubble backend.

Is it possible to create many records at once? +

Yes, the bulk_create_things tool allows you to create up to 1,000 records in a single call. You should provide the data in NDJSON format (one JSON object per line) for high-performance data ingestion.

How do I use the `get_thing` tool to retrieve detailed metadata for a specific Bubble item? +

You provide the Unique ID (UID) of the record you need. The MCP returns all associated fields and their current values, allowing your agent to inspect every detail about that 'Thing' without needing to run a full search.

What is the difference between using `update_thing` versus `replace_thing` when I modify existing data? +

Use update_thing (Patch) when you only want to change specific fields, leaving all other data intact. If you use replace_thing (Put), be careful because any field you omit will reset to its default value or get cleared.

If my `create_thing` call fails, what kind of error message should I expect from the MCP? +

The response payload includes specific error codes and a clear message detailing why the operation failed. This helps you instantly figure out if it was due to invalid data types or missing required fields.

When calling `create_thing`, how can I ensure that all required fields for a Bubble database type are included? +

You must include every field marked as mandatory in the JSON object you send. The MCP enforces schema validation, so if any required data is missing, the operation will fail before writing anything to the database.

If I run a massive search using `search_things`, what should I do if I hit rate limits? +

The MCP response will signal a rate limit error. You need to implement exponential backoff in your agent logic, pausing and retrying the request after an increasing delay until the operation succeeds.

Connect to your AI in seconds.

Bulk create things

Create thing

Delete thing

Bubble.io (No-code Application Platform API) - 8 Tools

Make your AI actually useful.

Bulk Create Things

Create Thing

Delete Thing

Get Thing

Replace Thing

Search Things

Trigger Workflow

Update Thing

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Managing app data used to mean jumping between tabs and running manual queries.

The `trigger_workflow` tool executes backend business logic.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Auditing a user account

Processing large data imports

Automating payment failure handling

The honest tradeoffs

Overwriting necessary data

Forgetting required IDs

When It Fits, When It Doesn't

Questions you might have