{
  "markdown": "# afya-mcp\n<!-- mcp-name: io.github.gabrielmahia/afya-mcp -->\n\n[![afya-mcp Glama score](https://glama.ai/mcp/servers/gabrielmahia/afya-mcp/badges/score.svg)](https://glama.ai/mcp/servers/gabrielmahia/afya-mcp)\n[![smithery badge](https://smithery.ai/badge/@gabrielmahia/afya-mcp)](https://smithery.ai/server/@gabrielmahia/afya-mcp)\n\n\n---\n**Compatible with `claude-sonnet-5`** (released 2026-06-30) — Anthropic's most agentic\nSonnet yet. Runs multi-step tool chains end-to-end without stopping short.\nInstall: `pip install afya-mcp` · Use with any MCP client.\n\n---\n\nMCP server for Kenya health system navigation — NHIF coverage, facility finder, maternal health, CHW support, and essential medicines. 6 tools.\n\n## Part of the East Africa Coordination Stack\n\nThis MCP server is one of 32 tools in the Kenya coordination infrastructure.\nIt connects to [`africa-coord-bus`](https://github.com/gabrielmahia/africa-coord-bus) — the coordination\nevent bus that routes signals between domains automatically.\n\nWhen this server detects a threshold condition, the bus notifies:\n- `bima-mcp` — parametric insurance evaluation\n- `kilimo-mcp` — agricultural advisory\n- `afya-mcp` — health surveillance activation\n- `county-mcp` — county office alert\n\n```python\npip install africa-coord-bus\n```\n\nAll servers: [pypi.org/user/gmahia](https://pypi.org/user/gmahia/)\n## AI Architecture: Health Domain RAG\n\nMedical AI requires grounding — ungrounded responses in health contexts cause real harm.\nUse this server as a **RAG entry point**, not a standalone health oracle.\n\n**Research basis:**\n- *RAG Best Practices for Medical Domain* (2026): RAG outperforms chain-of-thought\n  on complex medical reasoning and is more interpretable — critical in clinical contexts.\n- *AfricaNLP 2025/2026*: Only 4 African languages (incl. Swahili) have consistent\n  NLP support. Healthcare is identified as the highest-priority domain needing\n  accurate, grounded AI — and the one with the most critical data gaps.\n- *Multilingual NLP for African Healthcare* (AfricaNLP 2025): Bias and translation\n  errors persist specifically in African health AI contexts.\n\n**Appropriate use:**\n✅ Health facility navigation, NHIF coverage lookup, community health worker support  \n✅ Health information grounded in verified Kenya health system data  \n✅ Triage to appropriate care level  \n❌ Diagnosis, prescription, or clinical decision-making (human-in-the-loop required)\n\n## IP & Collaboration\n\nMIT 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](docs/architecture/IP_POLICY.md). Security reports: see [SECURITY.md](SECURITY.md).\n\n<!-- interconnect:v1 -->\n## Part of the East Africa coordination stack\n\n- **Install & run:** `pip install reli-cli && reli list` — 33 MCP servers on the [official MCP Registry](https://registry.modelcontextprotocol.io) under `io.github.gabrielmahia`\n- **Evaluate any model on Swahili agent tasks:** [kipimo](https://github.com/gabrielmahia/kipimo) · [dataset](https://huggingface.co/datasets/gmahia/kipimo) · [leaderboard](https://huggingface.co/spaces/gmahia/kipimo-leaderboard)\n- **Coordinate across servers:** [africa-coord-bus](https://pypi.org/project/africa-coord-bus/) — offline-first event bus with a built-in Kenya routing table\n- **Datasets:** [huggingface.co/gmahia](https://huggingface.co/gmahia) · **Docs hub:** [nairobi-stack](https://github.com/gabrielmahia/nairobi-stack)\n\nModel-agnostic by design: closed APIs, open-weight models, and small distilled models are all first-class citizens.\n<!-- /interconnect:v1 -->\n",
  "bytes": 3656,
  "sha": "95734485332fe895731c238b0047a44a7e990ccc996a81ed4f9b332325717652",
  "repo_slug": "gabrielmahia/afya-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_gabrielmahia_afya_mcp_612a0b35/readme"
}