Repository avatar
AI Tools
v0.1.14
active

afya-mcp

io.github.gabrielmahia/afya-mcp

Kenya health system guides: SHA/SHIF coverage, facility templates, maternal care, CHWs. Demo data.

Documentation

afya-mcp

afya-mcp Glama score

Install: pip install afya-mcp · Use with any MCP client.

MCP server for Kenya health system navigation — SHA/SHIF coverage, facility finder, maternal health, CHW support, and essential medicines. 7 tools.

Live data

  • dhs_health_indicator: official Kenya DHS 2022 figures (vaccination, stunting, skilled birth attendance, modern contraception, under-five mortality), nationally or by county, via the DHS Program API.

Each live answer names its source, attribution and retrieval time; if a service does not answer, the tool returns an error instead of a number. The other tools are unchanged.

Part of the East Africa Coordination Stack

This MCP server is part of the Kenya coordination infrastructure. It connects to africa-coord-bus — the coordination event bus that routes signals between domains automatically.

When this server detects a threshold condition, the bus notifies:

  • bima-mcp — parametric insurance evaluation
  • kilimo-mcp — agricultural advisory
  • afya-mcp — health surveillance activation
  • county-mcp — county office alert
pip install africa-coord-bus

All servers: pypi.org/user/gmahia

AI Architecture: Health Domain RAG

Medical AI requires grounding — ungrounded responses in health contexts cause real harm. Use this server as a RAG entry point, not a standalone health oracle.

Research basis:

  • RAG Best Practices for Medical Domain (2026): RAG outperforms chain-of-thought on complex medical reasoning and is more interpretable — critical in clinical contexts.
  • AfricaNLP 2025/2026: Only 4 African languages (incl. Swahili) have consistent NLP support. Healthcare is identified as the highest-priority domain needing accurate, grounded AI — and the one with the most critical data gaps.
  • Multilingual NLP for African Healthcare (AfricaNLP 2025): Bias and translation errors persist specifically in African health AI contexts.

Appropriate use: ✅ Health facility navigation, SHA/SHIF coverage lookup, community health worker support
✅ Health information grounded in verified Kenya health system data
✅ Triage to appropriate care level
❌ Diagnosis, prescription, or clinical decision-making (human-in-the-loop required)

IP & Collaboration

MIT licensed. Feedback via GitHub Issues only — pull requests are not accepted. Demo data is labeled DEMO and is not suitable for operational decisions. Full policy: docs/architecture/IP_POLICY.md. Security reports: see SECURITY.md.

Part of the East Africa coordination stack

Model-agnostic by design: closed APIs, open-weight models, and small distilled models are all first-class citizens.