Open to Your Architecture: APIs and MCP
Model Context Protocol (MCP)
Via MCP, the Enterprise AI Platform becomes the knowledge layer for assistants and agents not built by IntraFind – whether Microsoft Copilot, ChatGPT, Claude or your own agent frameworks.
- Permission-checked: Every MCP request is checked against the permissions of the signed-in user.
- Cited: Source citations are included.
This gives your assistants enterprise context without you having to build a second permission model.
REST APIs
Available as documented interfaces:
- Search
- Passage-level retrieval
- Generative answers
- Connectors
- Processing pipelines
Your own business applications build on exactly the same data and AI infrastructure as iFinder, iAssistant and iHub.
Data Science
Data science teams access the already processed, enriched and vectorized index data directly – for example from a Jupyter notebook – and use it for their own analyses, models or experiments.
- Permission-checked
- No data export into shadow copies
Developer Portal
API reference, how-tos, quickstart and reference architectures are available on request.
💡FAQ - APIs & MCP
Yes – every API and MCP request goes through the same permission check and returns the same source citations as iAssistant.
Secure, Sovereign, Compliant
✔️EU AI Act - The Enterprise AI Platform complies with the AI Act (Regulation (EU) 2024/1689)
✔️Data protection - GDPR-compliant operation
✔️No model training - Your data is not used to train AI models
✔️Data residency - You decide where your data is processed and stored
We Look Forward to Hearing from You
Bring us a specific use case – a search that takes too long, a question you want a chatbot to answer, or a process an agent could take over.
We’ll show you how to build it on the platform – and what becomes possible next without starting over.
