A multi-domain multi-agent system served over MCP (Model Context Protocol) with FastMCP, exposing specialized domain agents as tools to automate business workflows.
An MCP server with 60 tools connecting AI assistants to Czech healthcare databases (SUKL, MKN-10, NRPZS) and global biomedical sources (PubMed, ClinicalTrials.gov, OpenFDA).
A multi-purpose MCP server for AI-powered healthcare assistance that processes clinical data through configurable LLM providers. Maintains webhook endpoints for patient data processing with PostgreSQL logging and OpenAPI documentation.
Clinical decision-support MCP server that lets AI agents reason over live FHIR patient data for medication review, appointment scheduling, and care gap identification.
An MCP server that provides clinical decision support for polysubstance risk and drug–substance interactions, grounding LLM responses in a 7-level evidence cascade with population priors and validated screening triggers.
A privacy-preserving local RAG system integrated with MCP, enabling natural language queries over ingested documents and a SQLite database through vector search and local database tools.