Agentic AI & MCP – the next step for intel­li­gent process auto­ma­tion

Insiders is inten­si­vely engaged with the question of how arti­fi­cial intel­li­gence will work in the future. Instead of relying on a mono­li­thic “all-rounder model,” Insiders is deve­lo­ping Agentic AI—a network of spe­cia­lized agents that use the appro­priate tools depending on the process and make decisions inde­pendently. A central component in this deve­lo­p­ment is the Model Context Protocol (MCP).

What is an MCP?

Until now, every external connection—whether API, database, or OCR service—had to be developed indi­vi­du­ally. This approach was time-consuming, prone to errors, and made it difficult to reuse existing solutions.

The Model Context Protocol stan­dar­dizes this access:
An agent can access different servers via MCP without requiring a separate inte­gra­tion for each con­nec­tion. Each server provides precisely defined tools—for example, an OCR function, an email service, or an SAP connection—as well as resources such as files or documents. The agent dyna­mi­cally decides which tools are necessary for the task at hand and combines them into a struc­tured work plan. This allows processes to be imple­mented, reused, and flexibly adapted more quickly.

The vision

OvAItion’s AI models and OmnIA’s functions – including OCR, document analysis, and other auto­ma­tion tools – will in future be available directly as tools for an LLM. Pre­de­fined work plans in the form of prompt templates define exactly how, for example, an e‑invoice is to be processed: which steps are to be taken, in what order, and with which tools.

Instead of pro­gramming rigid processes, Insiders develops tools and precise gui­de­lines that the LLM combines and executes depending on the situation. This keeps the process flexible without losing precision.

Relevance for customers

Simpler inte­gra­tion
With MCP, a one-time imple­men­ta­tion is all it takes to make your own tools usable for any number of AI agents—without addi­tional inte­gra­tion efforts for new projects.

Greater fle­xi­bi­lity
New functions or systems can be connected quickly and easily without having to make costly adjus­t­ments to existing processes.

A step toward true standards
MCP creates a uniform interface and reduces the pro­li­fe­ra­tion of indi­vi­dual isolated solutions, which brings long-term stability, com­pa­ti­bi­lity, and invest­ment security.

Current status

With projects such as the FHIR Starter, Insiders is already gaining expe­ri­ence in the deve­lo­p­ment of intel­li­gent AI agents. This enables the company to offer pro­to­types and pilot solutions at an early stage and secure a head start for its customers in the intro­duc­tion of this new tech­no­logy.