wapimaji-mcp
# π§ WapiMaji MCP β Kenya Water & Drought Intelligence
<!-- mcp-name: io.github.gabrielmahia/wapimaji-mcp -->
[](https://glama.ai/mcp/servers/gabrielmahia/wapimaji-mcp)
[](https://smithery.ai/server/@gabrielmahia/wapimaji-mcp)
---
**Compatible with `claude-sonnet-5`** (released 2026-06-30) β Anthropic's most agentic
Sonnet yet. Runs multi-step tool chains end-to-end without stopping short.
Install: `pip install wapimaji-mcp` Β· Use with any MCP client.
---
> MCP server giving AI agents real-time access to Kenya's water stress and drought data β all 47 counties, NDMA drought phase classifications, and SMS alert capability via Africa's Talking.
[](LICENSE)
[](https://python.org)
[](https://modelcontextprotocol.io)
## What it does
WapiMaji MCP exposes Kenya drought and water stress data as MCP tools. Any Claude, GPT-4, or MCP-compatible AI agent can now:
- Query live drought phase data for any of Kenya's 47 counties
- Get water stress indices from NDMA drought monitor
- Send SMS alerts to farmers via Africa's Talking when drought levels spike
**One-prompt examples:**
```
"What is the current drought phase in Marsabit County?"
β Gets NDMA Phase 3 classification + rainfall deficit data
"Which counties are in drought emergency right now?"
β Returns all counties at Phase 3+ with population affected
"SMS these 500 Garissa farmers: drought phase has escalated to 3"
β Sends alerts via Africa's Talking across Safaricom + Airtel
```
## Tools
| Tool | Type | Description |
|------|------|-------------|
| `get_drought_status` | Read-only | Current NDMA drought phase for a county |
| `get_county_water_stress` | Read-only | Water stress index, rainfall deficit, river levels |
| `get_drought_alerts` | Read-only | All counties at or above a given drought phase |
| `sms_drought_alert` | Destructive | Send drought alert SMS via Africa's Talking |
## Install
```bash
pip install wapimaji-mcp
# or:
uvx wapimaji-mcp
```
## Configure
```json
{
"mcpServers": {
"wapimaji": {
"command": "uvx",
"args": ["wapimaji-mcp"],
"env": {
"AT_USERNAME": "your_username",
"AT_API_KEY": "your_at_key",
"SANDBOX": "true"
}
}
}
}
```
## Data sources
- **NDMA** β National Drought Management Authority drought phase classifications
- **Kenya Meteorological Department** β rainfall data
- **FEWS NET** β Famine Early Warning System food security projections
## Related
- [mpesa-mcp](https://pypi.org/project/mpesa-mcp/) β M-Pesa + Africa's Talking MCP server
- [WapiMaji](https://wapimaji.streamlit.app) β The Streamlit dashboard version
- [gabrielmahia.github.io](https://gabrielmahia.github.io) β Full civic portfolio
## IP & Collaboration
Β© 2026 Gabriel Mahia Β· [contact@aikungfu.dev](mailto:contact@aikungfu.dev)
License: MIT
Not affiliated with NDMA or Africa's Talking.
## Data Sources
This server draws on open and public domain datasets for drought intelligence:
**Open Government Data (Public Domain)**
- NASA MODIS NDVI β vegetation index for drought early warning
- NOAA CHIRPS β daily rainfall estimates (0.05Β° resolution)
- NASA TRMM β monthly precipitation
- USDA FEWS NET β East Africa livelihood zones
**Historical Baseline Data (Public Domain)**
- East Africa Meteorological Records 1900-1940 (colonial era, PD)
- Kew Gardens East Africa Survey 1910 (botanical PD)
These are structured in [africa-open-climate-data](https://huggingface.co/datasets/gmahia/africa-open-climate-data)
and [east-africa-agricultural-pd](https://huggingface.co/datasets/gmahia/east-africa-agricultural-pd).
## Part of the East Africa Coordination Stack
This MCP server is one of 32 tools in the Kenya coordination infrastructure.
Connect it to [`africa-coord-bus`](https://github.com/gabrielmahia/africa-coord-bus) β
the coordination event bus that routes signals between domains automatically.
```bash
pip install africa-coord-bus
```
All 32 servers: [pypi.org/user/gmahia](https://pypi.org/user/gmahia/)
Live demo: [coord-cascade-demo](https://github.com/gabrielmahia/coord-cascade-demo)
<!-- interconnect:v1 -->
## Part of the East Africa coordination stack
- **Install & run:** `pip install reli-cli && reli list` β 33 MCP servers on the [official MCP Registry](https://registry.modelcontextprotocol.io) under `io.github.gabrielmahia`
- **Evaluate any model on Swahili agent tasks:** [kipimo](https://github.com/gabrielmahia/kipimo) Β· [dataset](https://huggingface.co/datasets/gmahia/kipimo) Β· [leaderboard](https://huggingface.co/spaces/gmahia/kipimo-leaderboard)
- **Coordinate across servers:** [africa-coord-bus](https://pypi.org/project/africa-coord-bus/) β offline-first event bus with a built-in Kenya routing table
- **Datasets:** [huggingface.co/gmahia](https://huggingface.co/gmahia) Β· **Docs hub:** [nairobi-stack](https://github.com/gabrielmahia/nairobi-stack)
Model-agnostic by design: closed APIs, open-weight models, and small distilled models are all first-class citizens.
<!-- /interconnect:v1 -->
TDQS
Scored across 3 tools
Each tool has a distinct purpose: retrieving counties by drought phase, getting detailed status for a specific county, and sending an SMS alert. There is no overlap or ambiguity.
Tool names mostly follow a verb_noun pattern, but 'sms_drought_alert' uses 'sms' as a verb while 'get_drought_alerts' and 'get_drought_status' use 'get'. This minor inconsistency prevents a perfect score.
With only 3 tools, the server is tightly scoped to its purpose of drought alerting for Kenya. Each tool earns its place and the count is appropriate for the domain.
The tool set covers core needs: querying alerts, detailed status, and sending alerts. Minor gaps like listing all counties or historical data exist but are not critical for the primary use case.