bima-mcp
MCP server for Kenya insurance intelligence, providing tools to query insurance products, NHIF coverage, and parametric crop risk scoring.
README
🛡️ bima-mcp — Kenya Insurance Intelligence MCP Server
First insurance intelligence MCP server for East Africa.
Exposes Kenya insurance data, NHIF coverage analysis, parametric crop risk scoring, and microinsurance comparison through the Model Context Protocol.
Why Insurance Infrastructure Matters
In mature economies, insurance is invisible infrastructure — it enables risk-taking by capping downside. A farmer plants a new crop because crop insurance limits loss. A parent starts a business because health insurance protects the family. Without this floor, the rational choice is perpetual caution.
Kenya's insurance penetration: 2.3% of GDP vs 8–11% in developed markets. The gap is not cultural — it is the cost of distribution, claims verification, and actuarial data. All three can be compressed by technology.
Tools
| Tool | What it does |
|---|---|
kenya_insurance_products |
List IRA-registered products by type (health, life, crop, device) |
nhif_coverage_query |
Query NHIF benefits by hospital tier and procedure type |
premium_estimate |
Estimate monthly premiums for any coverage type + income bracket |
parametric_crop_risk |
NDMA-based crop insurance risk for smallholder farmers |
compare_microinsurance |
Compare affordable products by target group and budget |
community_pool_calculator |
Size a chama pooled insurance arrangement |
Quick Start
pip install bima-mcp # coming soon to PyPI
bima-mcp # starts the MCP server on stdio
Claude Desktop Integration
{
"mcpServers": {
"bima-mcp": {
"command": "bima-mcp"
}
}
}
Use Cases
- Farmers: "What crop insurance do I need for my 2-acre maize farm in Nakuru?"
- Informal workers: "What NHIF tier 4 inpatient coverage do I get for KES 500/month?"
- Chama treasurers: "How do I set up pooled hospitalization cover for 25 members?"
- Researchers: "Compare parametric crop insurance risk across Kenya counties"
Research Basis
- ACRE Africa Parametric Crop Insurance Methodology (2023)
- Kenya IRA Annual Report 2024
- World Bank Insurance Primer for Low-Income Markets (2023)
- NDMA County Drought Monitoring Reports
⚠️ Disclaimers
DEMO data — not real insurance products or binding quotes. Not affiliated with NHIF, IRA, or any insurance provider. Always consult a licensed IRA-registered insurance agent for actual products. Kenya IRA: ira.go.ke
© 2026 Gabriel Mahia / AI Kung Fu LLC · MIT License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.