Bubble.io API MCP. Manage records and trigger workflows via chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Bubble.io (No-code Application Platform API) MCP Server gives your AI client full CRUD access to your Bubble database. You can create, read, update, and delete any 'Thing' record, plus execute complex backend workflows.
Use it to query data with custom constraints, manage bulk records, or trigger payments and emails directly via chat.
What your AI agents can do
Bulk create things
Creates multiple 'Thing' records simultaneously using a high-performance endpoint.
Create thing
Creates a single new 'Thing' record in the Bubble database.
Delete thing
Deletes a specific 'Thing' record from the Bubble database.
Find specific 'Thing' records by applying complex filters, pagination, and sorting parameters.
Instantly generate one or more new 'Thing' records in the database.
Update specific fields on an existing 'Thing' record, or completely overwrite its data.
Remove 'Thing' records entirely from the database.
Trigger pre-built backend workflows—like sending emails or processing payments—by name.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Bubble.io API MCP Server: 8 Tools for Data & Workflows
These tools allow your AI agent to perform every core database operation—from simple lookups to massive bulk data creation—and execute backend workflows defined in your Bubble application.
019e5d04bulk create things
Creates multiple 'Thing' records simultaneously using a high-performance endpoint.
019e5d04create thing
Creates a single new 'Thing' record in the Bubble database.
019e5d04delete thing
Deletes a specific 'Thing' record from the Bubble database.
019e5d04get thing
Retrieves all metadata for one specific 'Thing' using its Unique ID (UID).
019e5d04replace thing
Replaces an entire existing 'Thing' record, resetting any missing fields to default values.
019e5d04search things
Searches, paginates, and sorts 'Thing' records using complex constraints in the database.
019e5d04trigger workflow
Starts a pre-built backend API workflow within the Bubble application.
019e5d04update thing
Updates (patches) specific fields on an existing 'Thing' record.
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
Make Your AI Do More
Start with Bubble.io (No-code Application Platform API), then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
Your AI client gets full CRUD access to your Bubble database with this server. You'll be able to create, read, update, and delete any 'Thing' record, plus kick off complex backend workflows. You can query data with custom constraints, manage bulk records, or even trigger payments and emails directly from a chat.
Search and Filter Records
Use search_things to search, paginate, and sort 'Thing' records. You can apply complex filters to narrow down exactly what you need. To get data for just one specific 'Thing', use get_thing and feed it the Unique ID (UID).
Create New Records
Need to generate new data? You've got a few options. Use create_thing to drop a single new 'Thing' record into the database. If you're dealing with a bunch of records, bulk_create_things handles creating multiple 'Thing' records at once using a high-performance endpoint.
Modify Existing Records
When you need to change data, you've got ways to do it. You can use update_thing to patch specific fields on an existing 'Thing' record without touching anything else. If you want to completely overwrite all the data, use replace_thing to reset the whole record.
Delete Records
Want to wipe a record clean? Use delete_thing to remove a specific 'Thing' record from the database entirely.
Execute Business Logic
This server lets you trigger pre-built backend API workflows by name using trigger_workflow. This means your agent can run complex business logic—like sending emails, processing payments, or updating status fields—without you writing API calls.
How Bubble.io API MCP Works
- 1 Subscribe to the Bubble.io API and provide your Bubble App URL and API Token.
- 2 Your AI client sends a request describing the desired data action (e.g., 'Update John Doe's status to Active').
- 3 The agent calls the appropriate tool (e.g.,
update_thing) and returns the confirmation or the requested data.
The bottom line is, your AI agent speaks Bubble's API language, letting you manage data and automate processes without touching the UI.
Who Is Bubble.io API MCP For?
This is for the developer or operations person who needs to run data fixes or extract reports without logging into the web app. If you're tired of clicking through dashboards and manually copying IDs, this server gives your agent direct database access.
Use the agent to pull quick reports ('Find all records where status is Pending') or update settings ('Change the default tax rate to X') using simple chat commands.
Debug data issues, run migrations, or test backend workflows directly from your chat client instead of leaving the development environment.
Automate repetitive data entry or trigger maintenance workflows (like processing a batch of refunds) using natural language prompts.
What Changes When You Connect
- Bulk Data Handling: Stop doing records one by one. Use
bulk_create_thingsto generate up to 1,000 records in a single, fast request. - Targeted Updates: Need to fix one field on 50 records? Use
update_thingto patch specific data points without affecting other fields. - Deep Searching: Don't rely on basic filters.
search_thingslets you query your database with complex constraints, custom sorting, and pagination. - Automation on Demand: Instead of building a separate job, use
trigger_workflowto execute complex business logic—like sending emails or processing payments—with a single command. - Full Lifecycle Control: The server supports the entire CRUD cycle. You can
create_thing,get_thing,update_thing, anddelete_thingall through your agent. - Developer Debugging: When testing new features, use the server to run migrations or test backend workflows without ever leaving your chat window.
Real-World Use Cases
Need to find all active user accounts in a specific region.
The Product Manager asks their agent: 'Find all 'user' records where the status is Active and the region is California.' The agent uses search_things to query the database, returning a list of UIDs and basic details. The PM can then ask for the full details on specific UIDs using get_thing.
Onboarding a batch of new clients after a sale.
The Operations Engineer needs to create 50 new 'client' records. They instruct the agent to use bulk_create_things, passing the necessary JSON data for all 50 records at once. This ensures rapid, high-volume data entry without writing a script.
Processing refunds for a batch of transactions.
The agent needs to process refunds. The user tells the agent to 'Process refunds for the last 10 transactions.' The agent calls trigger_workflow with the necessary transaction ID, executing the full payment processing and logging logic defined in the backend workflow.
Fixing a single user's payment method manually.
A developer discovers a bug in one user's profile. They tell the agent to update_thing for the user's specific UID, changing only the payment method field. This fixes the data without requiring a full app deployment.
The Tradeoffs
Treating the API like a simple lookup.
Asking the agent to 'Get the user and then update their address' in two separate calls. This is inefficient and risks race conditions if the data changes between calls.
→
If the operation is atomic, try to combine the intent. If you need to create and update, use create_thing followed immediately by update_thing in a single, chained prompt. For complex changes, look at trigger_workflow.
Over-relying on `get_thing` for lists.
Trying to retrieve a list of 50 'Product' records by calling get_thing 50 times. This is slow and hits rate limits fast.
→
Always use search_things when you need a collection of records. Use its constraints and pagination features to pull large datasets efficiently.
Trying to manage data without tracking the result.
Calling create_thing and assuming the data is there. If the creation fails, the user won't know why.
→ Always review the response. The server returns the UID or a success message, which tells you if the data exists and if the operation completed successfully.
When It Fits, When It Doesn't
Use this server if your core problem is data state management. You need to interact with or change records in Bubble.io without using the web UI. You'll use it when you need to run a scheduled job, debug a data point, or trigger a complex backend process.
Don't use it if you just need to view data that is already perfectly structured and easily queryable via a simple API endpoint—a dedicated read-only data source might be better. Also, if your business logic relies on specialized, non-Bubble services (like a specific legacy CRM), you might need to build a wrapper around this server to handle the orchestration, as it only handles Bubble's internal state.
The server is best for transactional work: 'I need to make X happen to Y data.'
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
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 server provides 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually updating records across multiple dashboards is a huge time sink.
Today, if you need to change a user's subscription level or update a product setting, you're forced to log into the Bubble dashboard. You find the specific record, navigate to the right tab, and manually change the field. If you have to do this for dozens of users, it's a nightmare of clicks and copy-pasting IDs.
With this MCP server, you just tell your agent: 'Change the status of all users who signed up last month to Active.' The agent handles the complex logic, calling `search_things` and then `update_thing` across the board. You get the result back in a single chat confirmation.
Bubble.io API MCP Server: Run bulk and workflow ops from chat.
You eliminate the need to use the Bubble API documentation to build complex JSON payloads for bulk operations. You simply ask for the action, and the agent structures the call using `bulk_create_things` or `trigger_workflow` for you.
This isn't just a data tool; it's a process automation layer. You can run a full payment sequence or data migration cycle without ever leaving your agent's interface. It's direct control.
Common Questions About Bubble.io API MCP
How do I search records using the Bubble.io API MCP Server's `search_things` tool? +
You pass the search parameters—like constraints, sorting, and pagination—as encoded JSON arrays in the tool call. You don't write SQL; you tell the agent what criteria you need, and it handles the complex filtering logic.
Can the Bubble.io API MCP Server's `bulk_create_things` handle more than 100 records? +
Yes, it is designed for high throughput. The endpoint supports creating up to 1,000 records in one request, making it ideal for data migrations or large-scale onboarding.
What is the difference between `create_thing` and `bulk_create_things`? +
Use create_thing when you only need to make one record. Use bulk_create_things when you need to process multiple records at the same time; it's much faster.
Can I trigger a workflow using the Bubble.io API MCP Server's `trigger_workflow` tool? +
Absolutely. This tool allows you to execute any pre-built backend API workflow by name, letting your agent handle complex tasks like payment processing or sending confirmation emails.
How do I update a single record using the Bubble.io API MCP Server's `update_thing` tool? +
You use the update_thing tool to modify an existing record. You must provide the record's Unique ID (UID) and a JSON object containing only the fields you want to change. Any fields you don't include remain untouched.
What kind of data must I provide when using the `get_thing` tool? +
The get_thing tool requires only the Unique ID (UID) of the specific record you want to retrieve. This ensures you pull down the exact metadata for that 'Thing' without ambiguity.
Does the `replace_thing` tool overwrite all fields in a record? +
Yes, replace_thing performs a full replacement (PUT) of the record. Be careful, because any fields you omit from the request will be reset to default values or cleared entirely.
Can the `search_things` tool handle complex filtering and sorting? +
The search_things tool supports complex querying. You can pass constraints using a URL-encoded JSON array, and you can also specify sorting criteria, pagination limits, and a cursor for deep searches.
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.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Text Readability Scorer
Calculate mathematically accurate readability metrics (Flesch-Kincaid, Gunning Fog, SMOG) for any text. Stop relying on AI 'feelings' — get exact US grade levels for SEO and compliance.
Honeycomb
Automate observability via Honeycomb — manage datasets, queries, and markers directly from any AI agent.
Gitpod
Automate cloud development environments — create, start, and manage Gitpod workspaces and organizations directly from any AI agent.
You might also like
Bureau of Labor Statistics Full — The Mega Server
The ultimate BLS Mega-Server: Access all 6 major datasets including CPI (Inflation), CES (Jobs), CPS (Unemployment), JOLTS (Turnover), LAUS (Local metrics), and OEWS (Wages by Profession).
HighLevel
Automate CRM and marketing via HighLevel — manage contacts, opportunities, and calendars directly from any AI agent.
Namsor
Automate name analytics via Namsor — predict gender, origin, and ethnicity directly from any AI agent.