Supercharge your AI with 4D. Talk to your database using plain language.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
4D MCP connects your 4D database directly to your AI client. This lets your agent explore data structures, query tables, and manage records without you writing a single REST call.
You can audit catalogs, run complex lookups across defined data classes, and perform high-speed CRUD operations entirely through conversation.
What your AI can do
Delete entity
Removes an entire record from a specified database table.
List entities
Queries multiple records from a table, supporting advanced filters and sorting rules.
Get entity
Fetches one specific record from a table using its unique primary key ID.
Retrieve the full list of available tables and their specific fields so you can map out your entire data model.
Fetch a single, identified record by its primary key for quick lookups.
Perform advanced searches across an entire table using filters, sorting rules, and joining related data.
Add entirely new records into any exposed database table.
Update the content of a record, changing specific fields without touching the rest of the data.
Permanently delete records from the database when they are no longer needed.
Ask an AI about this
Compatible AI Apps
OAuth 2.0 Compatible Gemini Waiting for input…
4D: Data Management Operations (6 Tools)
These six tools let your agent perform the full lifecycle of data management—from exploring tables to deleting individual records.
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 4D on VinkiusDelete Entity
Removes an entire record from a specified database table.
List Entities
Queries multiple records from a table, supporting advanced filters and sorting rules.
Get Entity
Fetches one specific record from a table using its unique primary key ID.
Create Entity
Adds a brand new record to the database table when given the necessary data payload.
Update Entity
Changes the data within an existing record by accepting new field values.
Get Catalog
Retrieves the full structural map of your database, listing all available tables and their fields.
Connect to your AI in seconds. 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 4D 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 4D, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ 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 4D. 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 6 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
The Pain of Manual Data Access
Think about how your team handles data today. You open the documentation, find the exact REST endpoint for the 'Customers' table, and then write boilerplate code just to read five records. If you need a different set of fields or want to filter by date range, you have to stop, manually adjust the URL parameters, and rewrite the entire function call. It’s repetitive, it's slow, and frankly, it’s overkill.
With this MCP, that boilerplate vanishes. You talk to your agent—you ask, 'Show me all customers who signed up last month.' The agent handles the complex logic of figuring out which table to query and what filtering parameters are needed. What you get is a clean answer without ever writing an HTTP request.
Using 4D MCP for Data Management Operations
The most time-consuming steps that go away are the manual schema lookups and the boilerplate code required to validate input payloads. You no longer have to map fields manually or worry about which specific endpoint handles a complex update—it's abstracted into natural language actions.
Your agent now manages your data lifecycle directly through conversation. It’s not just reading; it can reliably create new records via `create_entity` and manage updates with `update_entity`. That makes the entire system feel like one cohesive unit.
What your AI can actually do with this
Your 4D database is designed for structure. When working with it traditionally, you're stuck in the world of manual API calls—writing boilerplate code just to figure out what tables exist or how to format a single record update. This MCP changes that. It treats your entire data layer like an intelligent knowledge base.
Your agent can now talk to your database naturally; it doesn't need specific instructions for every field or table. You simply ask, and the system figures out the right operation. Because Vinkius hosts this integration, you get instant access to advanced query capabilities alongside basic entity management. You treat querying complex data like talking to a coworker who already knows where everything is stored.
019d7545-10c3-721d-92e4-a9ecd67dbfc0 
Here's how it actually works
The bottom line is, you tell your agent what you want; it figures out how to talk to the 4D database and gets it for you.
Subscribe to this MCP and provide your 4D Base URL credentials.
Direct your AI agent's attention to this MCP within any compatible client.
Ask the agent a question (e.g., 'Show me all orders for John Doe'). The agent handles the necessary operations in the background.
Who is this actually for?
Anyone who has to look at a database schema and translate that into code will appreciate this. It’s built for developers tired of writing repetitive data access boilerplate, or analysts who just want answers without knowing SQL syntax.
Needs to pull specific subsets of data (e.g., 'all invoices over $500 last month') for a report without writing complex joins or filtering logic.
Wants to test out new database access patterns or write migration scripts by just asking the agent to 'list all tables' and then running CRUD operations against them.
Needs to manage application records—like creating a new user account or updating an address—from a simple chat interface instead of navigating through multiple web forms.
What Changes When You Connect
Instead of writing custom code for every query, simply ask the agent to use list_entities with filters like '$filter'—it handles the complex ORDA syntax automatically. It’s a huge time saver.
Need to know what data structures you even have? Use get_catalog. It immediately gives you a full map of every table and field, saving you hours of schema investigation.
When your agent needs to make changes, it can use create_entity or update_entity. You don't need separate API endpoints for writes; the MCP handles it all in one flow.
Forget writing complex manual lookups. The tool allows advanced querying via list_entities, letting you search and sort records using natural language parameters like date ranges or status flags.
If a record is wrong, deleting it shouldn't be a process nightmare. You can use delete_entity right through the chat interface to clean up data without touching deployment code.
See it in action
Auditing Data Integrity
A developer needs to verify if all records in the 'Orders' table have a corresponding entry in the 'Customers' table. The agent first calls get_catalog to confirm the tables, then uses list_entities with complex filtering logic to identify missing foreign keys.
Generating Quarterly Reports
A data analyst needs a list of all 'Products' that were modified in Q1. They ask the agent, and it executes a filtered search using list_entities based on modification dates, pulling exactly the subset they need.
Onboarding New Users
A business admin has to create a new employee profile across three linked tables (User, Department, Contact). The agent manages this by calling create_entity sequentially for each required record, guaranteeing the primary keys link up correctly.
Debugging Application State
A QA engineer needs to see exactly what data is tied to a specific test case. They ask the agent to retrieve the full 'TestRun' entity using get_entity, instantly showing all related logs and metrics.
The honest tradeoffs
Treating the DB like an endpoint
Trying to write a simple script that makes three separate HTTP calls—one for listing, one for getting details, and a third for updating. This is fragile and verbose.
Instead of multiple explicit API endpoints, let your agent orchestrate the process using get_catalog first (to map schema), then use list_entities to gather data, and finally pass that data into update_entity—all in one conversational flow.
Over-relying on static code
Writing a hardcoded query that assumes the 'Invoices' table will always have an 'Amount' field, even if schema changes.
First, run get_catalog to verify the current structure. This ensures your agent adapts to real-time schema changes before attempting any operation like list_entities.
Mixing up read/write tools
Attempting to update a record by passing it directly into the listing query, which will fail because the tool expects data retrieval parameters.
Keep them separate. Use list_entities for reading and searching; use update_entity specifically when you have the primary key and the new fields ready for modification.
When It Fits, When It Doesn't
Use this MCP if your core problem is accessing structured, persistent data that requires full CRUD capabilities (Create, Read, Update, Delete). This works best with application backends or internal tools where the state lives in a defined database. Don't use it if you just need to read simple metrics from an external source like a spreadsheet API—a dedicated webhook connector is better. If your data layer is highly dynamic and lacks consistent schema definitions, this MCP will struggle because it relies on structured ORDA operations. Always check the tool definition: do you need to query specific records (get_entity), or are you looking for a full list with filters (list_entities)? Knowing that determines which tool you'll actually use.
Questions you might have
How does the 4D MCP work for listing all data? +
It uses the list_entities tool. You don't need to know complex ORDA syntax; you just tell your agent what table and what filters you want, and it handles the rest of the advanced querying.
Can I use 4D MCP to check my database structure? +
Yes. You simply ask the agent to look at the catalog, which triggers the get_catalog tool. It'll give you a full list of all available tables and their field definitions.
What if I only need one specific record? Should I use get_entity or list_entities? +
If you have the unique primary key, use get_entity. It’s faster. If you need to search for a record based on criteria (like 'email address'), then you should use list_entities.
Is 4D MCP safe for writing data? +
Yes, it's designed for controlled writes. Operations like creating or updating records are managed by the agent using tools such as create_entity and update_entity, ensuring consistency with your schema.
When I need to create or modify data, what format does `create_entity` require for the payload? +
It requires a JSON string representing the data. Make sure your JSON keys and values match the DataClass schema you first check using get_catalog. This ensures type safety when writing records.
If I'm querying a massive dataset, how does `list_entities` handle pagination or performance? +
The tool supports ORDA-style parameters like $filter and $orderby, letting you narrow down the search results. Always filter your request instead of trying to pull records without limits.
If I run several write commands, such as `delete_entity` followed by an `update_entity`, are they treated as a single transaction? +
No, the MCP executes each tool call independently. If you need to guarantee data integrity across multiple actions, your client logic must handle those steps sequentially.
Does using `get_catalog` or any other tool require me to manage API rate limits? +
Vinkius handles the connection management and throttling for you. You don't need to worry about hitting specific 4D server rate limits; your AI client manages the calls.
How do I find which tables are available? +
Use the get_catalog tool. It will return a list of all DataClasses (tables) exposed through the REST API in your 4D Server.
Can I filter data based on specific conditions? +
Yes. Use the list_entities tool and provide an ORDA-style filter string in the $filter parameter (e.g., "status = 'active' AND price > 100").
Does this support creating new records? +
Absolutely. Use the create_entity tool by providing the DataClass name and a JSON string containing the field data for the new record.
We've already built the connector for 4D. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 6 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.