Deta Space MCP for AI. Manage structured data and files conversationally.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Deta Space API manages your personal cloud storage directly from any AI agent. It gives you full conversational control over structured data in Deta Base and files in Deta Drive.
You can query NoSQL records, upload backups, list file contents, or perform atomic updates—all without opening a dashboard.
What your AI can do
Base delete item
Removes a specific item from Deta Base using its unique key.
Base get item
Retrieves and displays all attributes for one record in Deta Base, given the item's key.
Base insert item
Adds a new item to Deta Base only if no other item shares the same unique key.
Search Deta Base using complex criteria to pull specific JSON items without knowing their exact keys.
Upload, download, list, and delete files stored in your personal cloud drives conversationally.
Modify only a specific attribute of an existing database record, preventing you from accidentally overwriting the whole object.
Store new records in Deta Base or pull up any single item by its unique identifier.
Ask an AI about this
Waiting for input…
Deta Space (Serverless Personal Cloud API) with 10 Tools
These tools give your AI client full control over reading, writing, and organizing both structured records in Deta Base and files stored in Deta Drive.
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 Deta Space (Serverless Personal Cloud API) on VinkiusBase Delete Item
Removes a specific item from Deta Base using its unique key.
Base Get Item
Retrieves and displays all attributes for one record in Deta Base, given the item's...
Base Insert Item
Adds a new item to Deta Base only if no other item shares the same unique key.
Base Put Items
Writes one or more structured items into Deta Base from a JSON array input.
Base Query Items
Searches through Deta Base using complex query logic to find matching records.
Base Update Item
Changes specific fields of an existing item in Deta Base without affecting other attributes.
Drive Delete Files
Deletes one or more files from your personal cloud drive storage.
Drive Download File
Downloads a specified file from Deta Drive by its name.
Drive List Files
Returns a list of all files and folders currently stored in your Deta Drive.
Drive Upload File
Transfers a new file from your local machine into the Deta Drive storage.
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 Deta Space integration is available immediately — no restart needed.
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 Deta Space (Serverless Personal Cloud 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 Deta Space. 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 connection provides 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Manual Data Management is a Pain Point
Today, managing data means jumping between multiple interfaces. You open your cloud console to check file versions; then you switch to a dashboard GUI to see metrics, and finally, you have to manually copy the IDs into an API tool just to update one field. It's slow, it involves constant context switching, and it's easy to miss a step or overwrite the wrong data.
With this MCP, that process collapses. Your agent handles the clicks behind the scenes. You simply tell your AI client what you need—saying 'Update the project status and attach the final report.' It coordinates the necessary calls like `base_update_item` and `drive_upload_file`, giving you the result without leaving the chat.
You Get Full Control Over Your Personal Cloud
The biggest win is that you get full access to both your structured data and your file system. You don't have separate tools for 'database stuff' and 'file storage.' The whole thing runs together.
Now, whether you need to pull a single profile via `base_get_item` or upload an entire backup using `drive_upload_file`, it all feels like one natural extension of your conversation. It just works.
What your AI can actually do with this
This connector lets your agent manage all aspects of your personal serverless infrastructure through natural conversation. Think of it as getting an API gateway for your private cloud data and files, accessible right from your chat client. You can treat structured JSON records like notes in Deta Base—querying specific fields or even using tools like base_get_item to pull up a single user profile instantly.
It's the same conversation flow you use to ask about project status that lets you upload a new compliance document via drive_upload_file. Whether you're working in your IDE or just chatting with your agent, this gives you full access to your data and files. When you connect through Vinkius, you get all these capabilities rolled into one place, letting your AI client handle the plumbing for both structured records and actual file storage.
019e5d11-a790-728c-b76f-ec44defbfa97 
Here's how it actually works
The bottom line is that your AI client routes complex data and file operations through a single, simple conversation prompt.
First, subscribe to the MCP using your Deta Space App Key and Project ID credentials.
Your AI client then recognizes both data (Base) and file system (Drive) operations as available tools.
You simply ask your agent to perform an action—like 'Find my user profile from last week' or 'Upload this new report'—and the agent executes the required tool calls.
Who is this actually for?
This MCP is for the developer or engineer who gets tired of switching between documentation, a local terminal, and a cloud GUI just to manage state. If your job involves constant data inspection or file auditing, this saves you time.
Runs ad-hoc queries against NoSQL collections using base_query_items when the existing ETL pipeline fails and needs manual debugging.
Needs to build small backend features that require saving user settings or project metadata into Deta Base, without writing boilerplate API glue code.
Periodically audits personal cloud storage by listing files using drive_list_files and downloading logs for compliance checks.
What Changes When You Connect
Avoid overwriting data. Instead of using base_put_items which can replace an entire record, use base_update_item. This lets you target just the 'status' field for example, leaving all other metadata untouched.
Streamline file auditing. If you need to check what backups are available, run drive_list_files and get a clean list of everything in your drive without navigating folder structures.
Handle data lifecycle completely from chat. You can use base_insert_item to log a new event and then immediately follow up with drive_upload_file to attach the relevant supporting document.
Get fast read access. Need one user's profile? Use base_get_item by key. It bypasses complex querying and gives you the record instantly, which is faster than writing a dedicated search query.
Improve data integrity. If an item doesn't exist, use base_insert_item. This tool prevents accidental duplicates, ensuring your records are unique from day one.
See it in action
Need to update a user record.
The system admin needs to change a team member's 'role' and 'status' in the profiles collection. Instead of pulling the whole item, manually modifying it in an editor, and then pushing it back, they just ask their agent: 'Update user_102 role to manager and status to active.' The agent uses base_update_item.
Auditing old project files.
A compliance officer needs all the expense reports from Q3. They ask their agent, 'List all files in my finance folder for 2024.' The agent uses drive_list_files and then proceeds to drive_download_file for any file matching the required extension.
Logging a new incident.
An operations team member discovers an issue. They first ask the agent to 'Create a new incident log entry with key INC-9001.' The agent uses base_insert_item. Then, they use drive_upload_file to attach the error dump file and complete the record.
Finding related data points.
A data scientist wants all records where 'project' is Alpha AND 'status' is pending. They ask their agent, 'Query Deta Base for items matching project=Alpha and status=pending.' The agent executes base_query_items.
The honest tradeoffs
Using the wrong tool for file searches
A developer tries to use a database query like base_query_items to find files named 'report.pdf' inside their personal cloud drive, because they think it's a searchable field.
Don't try to query files in the base. File structure requires dedicated tools. To find files, you must use drive_list_files. If the file name is stored as text data, then you can search for it using base_query_items.
Overwriting entire records
A user reads a profile and only wants to change their phone number. They manually reconstruct the whole JSON object in memory and use a generic write function, risking accidental data loss.
Use base_update_item instead. This tool lets you specify exactly which attributes need changing (like 'phone_number') without having to retrieve or rewrite the rest of the item's data.
Deleting items manually
A user wants to delete a record, but they forget the unique key and try to pass in a partial identifier, leading to an API failure.
Always confirm the exact unique key. Use base_get_item first to verify the item exists and that you have the correct key before calling base_delete_item. It's a two-step confirmation process.
When It Fits, When It Doesn't
Use this MCP if your workflow requires interacting with both structured JSON data (like logs, user profiles) AND raw files (like PDFs, dumps). The core strength is combining these two operations through conversation. Don't use it if you only need to read a simple spreadsheet—a dedicated sheet connector is better. Also, don't rely on this for transactional integrity across multiple systems; think of it as a single data source interaction point. If your workflow involves complex, multi-join queries that require joining three or more different collections based on joins not explicitly defined in the tools (like base_query_items), you might hit limits and need a dedicated database platform instead.
Questions you might have
How do I update a record without losing data? (using base_update_item) +
You use base_update_item. This tool only modifies the attributes you specify, leaving all other existing fields in the item untouched. You don't have to retrieve and rewrite the whole object.
Can I search my files using base_query_items? +
No, base_query_items is for structured JSON data only. To find files or folders in your personal cloud drive, you must use drive_list_files.
What's the difference between base_insert_item and base_put_items? +
Use base_insert_item when you want to ensure the item key is unique before writing. If you use base_put_items, it will attempt to write multiple items in a single batch operation.
How do I delete files from Deta Drive? +
Use drive_delete_files. You tell the agent which file names or groups of files you want gone, and it handles the deletion across your drive storage.
If I use `base_get_item`, what happens if the key doesn't exist? +
The system returns an explicit error or null value. This means your AI client gets immediate feedback that no item was found by that specific key, so you can handle it in your workflow.
What information must I provide when using `drive_upload_file`? +
You need the file content, a unique name for the file, and optionally a descriptive category. The AI agent handles packaging these inputs so you can upload any type of file successfully.
Are there rate limits when I use `base_put_items` to store many records? +
Yes, while the MCP manages throughput, keep an eye on API response headers for usage quotas. If you hit a limit, your agent can retry the batch upload after waiting a short interval.
Does `base_delete_item` perform any kind of soft delete or confirmation? +
The tool performs an immediate, hard deletion by key. Use it only when you are absolutely certain that data should be permanently removed from Deta Base.
How can I search for specific records in a Deta Base? +
Use the base_query_items tool. You can provide a JSON array of query objects to filter items by their attributes, and even handle pagination using the limit and last parameters.
Can I update just one field in a database item without sending the whole object? +
Yes! The base_update_item tool allows you to perform atomic updates. You can use the set parameter to update fields, increment for numbers, or append for arrays.
How do I upload a text file or document to Deta Drive? +
Use the drive_upload_file tool. Provide the drive_name, the desired file name (path), and the content of the file. The agent will handle the storage process for you.
We've already built the connector for Deta Space. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.