4D MCP. Let your AI agent query and modify your 4D data.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
4D MCP Server connects your 4D database directly to your AI agent. It lets your agent explore data catalogs, run complex queries, and manage records via natural conversation.
Use it to audit data structures, run CRUD operations, and access all your 4D data without writing manual REST calls.
What your AI agents can do
Create entity
Inserts a new record into the database using a provided JSON payload.
Delete entity
Removes a specific record from the database.
Get catalog
Retrieves the full metadata definition of the 4D database structure.
Retrieves the full list of DataClasses (tables) and their fields, letting your agent understand the available data structure.
Fetches a single record using its primary key, confirming the existence and data points of an entity.
Performs complex queries across a DataClass, supporting filters, sorting, and joining related entities.
Builds and inserts a brand new record into a specified DataClass.
Updates the data payload of an existing record in the database.
Deletes a record from the database by its primary key.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
4D MCP Server: 6 Tools for Data Management
These tools let your AI agent perform every core data operation on your 4D database, from querying schemas to performing full CRUD actions.
019d7541create entity
Inserts a new record into the database using a provided JSON payload.
019d7541delete entity
Removes a specific record from the database.
019d7541get catalog
Retrieves the full metadata definition of the 4D database structure.
019d7541get entity
Gets the data for a single record using its unique primary key.
019d7541list entities
Queries and retrieves multiple records from a specified DataClass, supporting advanced filters and sorting.
019d7541update entity
Changes the data for an existing record using a provided JSON payload.
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 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
The 4D MCP Server connects your 4D database directly to your AI agent. It lets your agent explore data catalogs, run complex queries, and manage records using natural conversation. You can use it to audit data structures, run CRUD operations, and access all your 4D data without writing manual REST calls.
Your agent can first run get_catalog to get the full metadata definition of the 4D database structure, letting it understand what data's available. You can then use get_entity to fetch a single record using its unique primary key, confirming the data points and existence of any entity.
For running advanced data lookups, your agent runs list_entities to query and pull multiple records from a specified DataClass, supporting filters, sorting, and joining related entities. You can build and insert a brand new record using create_entity into any specified DataClass. You'll modify existing records by running update_entity, which changes the data payload of a record.
Finally, you can delete a record from the database by its primary key using delete_entity.
How 4D MCP Works
- 1 1. Subscribe to the 4D MCP Server and provide your 4D Server Base URL and credentials.
- 2 2. Your AI client invokes the tool (e.g.,
list_entities) using natural language prompts. - 3 3. The server executes the 4D API call and returns the structured data to your agent for action.
The bottom line is, your AI agent talks to the 4D database like it's a standard API, without you ever writing a single HTTP request.
Who Is 4D MCP For?
The data analyst who gets frustrated writing repetitive SQL queries just to build a simple report. The systems integrator who needs to verify API exposure during development. The business admin who needs to manage records across multiple tables from a single chat window. If your job involves reading data, this is for you.
Retrieves specific subsets of data for reports without writing manual HTTP calls or SQL.
Looks up and manages application records across different tables easily from a single chat interface.
Verifies REST API exposure and data availability in real-time during the building process.
What Changes When You Connect
- Audit your data structure instantly. Use
get_catalogto retrieve the full list of DataClasses and their fields. You don't need to check documentation to know what data exists. - Handle complex lookups without writing filters.
list_entitiessupports ORDA-style query parameters. You can ask for records based on multiple criteria (e.g., 'all invoices over $100 from last month'). - Manage the full data lifecycle. Use
create_entity,update_entity, anddelete_entityto handle records. Your agent manages the JSON payload for you. - Keep everything conversational. Instead of writing a multi-step API call (GET, then POST, then DELETE), you just ask your agent to 'update the customer email' and it runs the necessary tools.
- Get specific records fast. Need one invoice?
get_entityretrieves the record immediately by its primary key. It’s fast and targeted. - Reduce integration code. The MCP layer abstracts the raw REST API calls. You write one prompt, and the agent handles the underlying data access logic.
Real-World Use Cases
Finding an entity's structure
A new developer needs to know what data fields are available in the 'Products' table. Instead of reading the 4D API documentation or guessing, they prompt their agent: 'What tables do I have?' The agent runs get_catalog and lists all available DataClasses, saving hours of manual investigation.
Generating a monthly sales report
A data analyst needs the top 10 customers who placed orders over $5,000 in Q3. They tell their agent to 'list the top 10 customers with orders > $5k in Q3.' The agent uses list_entities with advanced $filter and $orderby parameters, returning a clean dataset for immediate reporting.
Onboarding a new user profile
A business admin needs to create a new user account in the 'Users' table and update their associated 'Permissions' table. They simply prompt: 'Create a user for John Doe and give him read/write permissions.' The agent runs create_entity and then update_entity sequentially, maintaining data integrity.
Correcting outdated data
A systems integrator finds a record that was accidentally deleted and needs to confirm its existence and current status. They ask the agent: 'Does a record with ID 1234 exist, and what is its current status?' The agent uses get_entity and provides the necessary metadata immediately.
The Tradeoffs
Manual REST Calls
The developer writes boilerplate code to call GET /catalog, then GET /entities/{id}, then manually constructs the body for POST /create for every single operation.
→
Use the 4D MCP Server. Let your agent handle the calls. Instead of writing the code for get_catalog, you just ask your agent: 'Show me the available data classes.' The agent executes the tool and returns the data.
Using the wrong tool for discovery
Trying to find out what tables exist by calling get_entity with a random ID, which will fail and gives no information about the schema.
→
Always run get_catalog first. This tool shows the full metadata definition, listing every available DataClass. This is the correct starting point for any data interaction.
Forgetting to handle errors
Writing a multi-step script that assumes every API call will succeed. If the update_entity fails due to bad data, the entire script breaks, and the data is left in an inconsistent state.
→ The agent manages the sequence. You prompt: 'Update X, but only if Y exists.' The agent coordinates the calls, handling the failure states and providing clear feedback, minimizing manual error handling.
When It Fits, When It Doesn't
Use this 4D MCP Server if your goal is to let an AI agent interact with 4D data using natural language. This is for building applications where the data access layer needs to be flexible and simple for the user, not the developer.
Don't use this if: You need to manage high-frequency, transactional data changes that require complex rollbacks across multiple services (you'd need a dedicated workflow orchestration platform like Kafka).
Use this if: You need basic CRUD operations, schema exploration, and complex lookups mediated by a natural language interface. The tools are atomic, making them perfect for building data-driven microservices where the client shouldn't care about the underlying 4D API calls.
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 server provides 6 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Talking to a database shouldn't require writing boilerplate API code.
Today, accessing 4D data means building custom REST calls. You have to write code that first hits the catalog endpoint, then builds query parameters for `list_entities`, then handles the response structure, and finally, writes a separate function for every single CRUD operation. It's complex, brittle, and requires a full-time developer just to handle the boilerplate.
With this MCP Server, you just let your agent talk to the database. You ask, 'Give me the invoices for John Doe.' The agent runs `list_entities` and returns the data. The whole process stays in the chat window, and the complexity vanishes.
4D MCP Server: Manage data classes & entities
Forget manually executing queries in a separate UI. You can now tell your agent to 'create a new customer' or 'update a product' and it runs the `create_entity` or `update_entity` tool immediately. The agent handles the JSON payload and the API specifics.
This isn't just a wrapper. It's a conversational layer that makes your 4D data immediately actionable. You get the full power of the 4D database without the manual steps of building a data access layer.
Common Questions About 4D MCP
How does the 4D MCP Server use the `list_entities` tool? +
The list_entities tool allows your agent to query records from a specific DataClass. You provide filters (like dates or status) and the agent handles the ORDA syntax for advanced lookups.
Can I use `get_catalog` to see what tables I have? +
Yes, get_catalog retrieves the complete metadata definition of your 4D database. It lists all DataClasses and their attributes, giving you a full map of your data structure.
What is the difference between `get_entity` and `list_entities`? +
Use get_entity when you know the exact primary key of a record. Use list_entities when you need to search for multiple records based on criteria like name or date.
Does the 4D MCP Server support creating new data? +
Yes. The create_entity tool allows your agent to generate and insert new records into any exposed DataClass.
What kind of data can the `update_entity` tool modify? +
The update_entity tool modifies existing records. You must provide the record's unique identifier and a JSON payload with the fields you want to change.
How do I handle errors when I use the `list_entities` tool? +
The list_entities tool reports standard HTTP status codes and includes a detailed error message in its output. If a query fails, the output will specify the reason, like invalid filters or missing DataClasses. This lets your AI client handle the failure gracefully.
What format does the `create_entity` tool require for the data payload? +
The create_entity tool requires the data payload as a JSON string. This JSON must match the structure of the target DataClass, including necessary fields and correct data types. Always validate your JSON before invoking the tool.
Does the `update_entity` tool support partial updates? +
Yes, the update_entity tool supports partial updates. You only need to provide a JSON payload with the fields you intend to change, leaving the rest of the record intact. Just make sure to include the primary key for the record you're modifying.
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.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Render Alternative
Automate your PaaS infrastructure via Render — list your services, deploy code, check logs, and scale resources directly from any AI agent.
Resend
Automate email delivery via Resend — send emails, manage domains, and track audiences directly from any AI agent.
OKLink (Multi-chain Web3 Blockchain Data API)
Access real-time blockchain data across multiple chains—query addresses, tokens, transactions, and blocks directly from your AI agent.
You might also like
Temporal
Monitor and manage distributed workflows in Temporal Cloud natively via your AI agent.
Incident.io
Manage incidents, roles, and on-call schedules via Incident.io API.
Yousign
Secure electronic signatures for documents and contracts with AI using Yousign V3.