Integrated MCP server

The integrated MCP server in NET Genium

Every NET Genium instance includes an integrated MCP server (Model Context Protocol). Through it, an AI assistant or agent – Claude or its developer variant Claude Code, ChatGPT or its developer variant Codex, Microsoft Copilot Studio or any other tool supporting the MCP protocol – connects to the instance and gets everything it needs to work with a particular implementation: the data of its applications, a description of how the applications are built, and the knowledge of the NET Genium framework.

The server is part of the installation, there is nothing to install or start separately. The procedure for connecting the individual AI tools is provided in the separate guide Connecting an AI tool to the MCP server.

What the server can do

• Working with data – reading and searching records and counting them, including the change history and attachments; with the write permission also creating, updating and deleting records.
• Describing the implementation – which applications, edit forms, view pages and rights the instance contains and how they relate to one another. The assistant is given the AI model of the implementation directly by the server, always in its current form – nothing is downloaded or pasted by hand.
• Building and changing applications – with the write permission, an agent can not only describe applications but also create them and keep changing them: application groups, applications, edit forms, view pages, controls, database queries and scripts.
• User settings – the layout of the portlets on the home page, favourite items and the individual settings of view tables can be read for any user and, with the write permission, set for individual users as well as for whole user groups. Details are provided in the chapter User settings.
• The knowledge of the framework – the assistant looks up and reads the relevant chapters of the NET Genium documentation, so it designs solutions according to the standards of the platform rather than to general habits. The knowledge base of the server is a selection from the documentation; the complete documentation is available in the AI assistant on the web.
• Performance analysis – directly from the running instance, the assistant finds out which pages, queries and scripts take the longest, how large the tables they run over are, and where indexes are missing. The usage statistics are collected only when logging to the database is turned on in the NET Genium settings.

An assistant with access to the data can therefore answer questions that the description of the applications alone cannot – for example “how many records exist”, “find a specific document” or “how did a record change over time”.

Access to the server

The MCP server is intended for the administrators of the instance – only a user with administrator rights may use it, and if the Administrators with access to the MCP server list is filled in the NET Genium Settings, only the Administrator account and the administrators in the list. The license key of the instance must allow AI; this is not required in NET Genium Online. Every request signs in as a particular user and may do only what that user's permissions allow. The AI tool authenticates in one of two ways:

• With a personal MCP token – administrators generate it themselves: they click the avatar on the right side of the header and choose MCP token in the personal menu. This way works with any instance and also suits an agent running unattended.
• By signing in – in the Claude and ChatGPT applications it is enough to enter the address of the instance and sign in; no token is copied anywhere. This way is available only on instances running at the root of the web site over HTTPS, so always in NET Genium Online.

What the AI tool may do is determined by the permissions of the token, or by the consent given when signing in:

The knowledge of the framework is given to every administrator regardless of the permissions ticked – it is the general documentation of the platform, not the content of the instance. Access to the server can be narrowed down to selected administrators only. A detailed description of this restriction is provided in the separate guide NET Genium settings.

Writing data through the MCP server

Writing through the MCP server does not run the scripts of the edit form – so neither the validations, recalculations, notifications nor status changes that follow saving a record take place. The record is created, but the process logic around it is not. Data whose saving such logic follows therefore belongs in the edit form, even on a development instance; other data can be written through the MCP server in production as well.

Moreover, a new record has no owner unless the agent states it explicitly among the values it writes. Encrypting values is likewise ensured only by the edit form: the value of a column with encryption turned on (the TextArea and RichTextBox controls) is written unencrypted through the MCP server, and reading returns the values as they are stored in the database.

By default, writing is not recorded in the change history and does not take part in synchronization – which suits bulk batches, typically sample data. For changes that have to stay traceable, writing with the change history therefore has to be requested explicitly. The same applies to deleting records: by default, a deletion is not recorded in the change history and does not take part in synchronization. When deleting with the change history, the records are deleted one by one, and the deletion is recorded in the history and sent for synchronization just like a deletion in the edit form; the scripts of the edit form do not run even then.

In NET Genium Online the server refuses writing while the instance is in read-only mode (credit used up or data allowance exceeded).

User settings

The layout of the portlets on the home page, favourite items and the individual settings of view tables are otherwise changed by users only themselves in the NET Genium user interface. Through the MCP server, an agent reads them for any user and, with the write permission, sets them for individual users as well as for all members of selected user groups; typically, it prepares the home page layout for a new group or adds a portlet to all of its members.

• Portlets and favourite items can be replaced entirely, or selected ones can just be added or removed. The refresh interval of the home page, the display of the image and the display of favourite items on the home page stay as each user has them, unless the agent changes them explicitly.
• The settings of a view table correspond to what users can customize on it themselves – the displayed columns and detail columns, sorting, the number of records per page and the displayed parts of the table; for a view table in a portlet, tooltip columns instead of detail columns. Composite filters are not set through the MCP server, and a statistics view table is not supported yet. The settings of a view table cannot be saved for the anonymous user, just as in the user interface.
• Users get only what they have rights to – a portlet, favourite item or column they have no right to is removed by the server after writing, and the response states it for the user concerned.

Security

• Every request signs in as a particular user – the owner of the token, or the one who allowed the AI tool by signing in – and is subject to the allowed IP addresses and to licences just like a regular login.
• Permissions are verified on every request – losing administrator rights ends the access immediately.
• Changes to applications are subject to the same restrictions as the configuration dialogs of the admin mode – what an administrator may not change in a dialog cannot be changed through the MCP server either.
• A token is valid for 90 days and can be deleted at any time; an application connected by signing in can be disconnected at any time.
• The server is protected against token guessing.
• The write permission allows any data of the instance to be changed, not just a selected table or the user's own records – it should therefore be turned on deliberately and only for those who need it.

Typical use cases

• natural-language questions about data – “find projects without a responsible person”, “how many invoices are added each month”,
• consistency checks and summary analyses of data across applications,
• finding out when and how a record changed,
• orientation in an implementation – how the application is built and which tables and columns belong to it,
• building new applications and changing existing ones,
• preparing the home page, favourite items and view tables for whole groups of users,
• performance analysis – which pages, queries and scripts take the longest and how large the tables they run over are,
• checking how a particular thing is properly done in the NET Genium framework before designing anything.

This server is naturally followed by agentic development – working with an AI agent that knows both the framework and the particular implementation and can work in it purposefully.