Afro.tools MCP Server
Provides AI agents with structured, verified specs for African APIs like Wave and Paycard, enabling automatic integration code generation without manual documentation parsing.
README
Afro.tools — AI-ready infrastructure for African APIs
Integrate Wave, Paycard, and any African API in a single prompt.
African APIs are production-grade. What's been missing is a standard, machine-readable format that AI agents can consume directly — without parsing documentation pages or guessing at request shapes.
Afro.tools fills that gap: a static, open-source registry of structured specs for African APIs. Each spec is verified against the live API and exposes exactly what an AI agent needs to generate correct integration code on the first try.
How it works
graph LR
A["specs/ — open source"] -->|GitHub raw URLs| B["MCP server\nmcp.afro.tools"]
B -->|MCP protocol| C["AI agent\nClaude · Cursor · Copilot · ..."]
C -->|generates| D["Integration code\nin your app"]
A -->|plugin| C
What is a spec?
A spec lives at specs/{category}/{provider}/{capability}/ and contains exactly two files:
schema.json— ATSS-compliant description of the API capability (endpoint, auth, input/output schemas, gotchas)canonical_example.ts— TypeScript implementation using native fetch, compiles withtsc --noEmit
Each provider also has a provider.json at the root of its folder:
specs/payment/paycard/
├── provider.json ← metadata + description + example_prompt
├── create_payment/
│ ├── schema.json
│ └── canonical_example.ts
├── verify_payment/
└── webhook_payment_completed/
See ATSS.md for the full specification.
Providers
<!-- tableau généré automatiquement par le pipeline — ne pas éditer manuellement -->
| Provider | Category | Country | Capabilities | Status |
|---|---|---|---|---|
| Paycard | payment | 🇬🇳 | 3 | ✅ AI Ready |
| Djomy | payment | 🇬🇳 | 7 | 4 verified · 3 ready |
| LengoPay | payment | 🇬🇳 | 8 | 2 verified · 6 ready |
| Flutterwave | payment | 🇳🇬 🇬🇭 🇰🇪 +10 | 57 | 📋 Ready |
| NimbaSMS | sms | 🇬🇳 | 11 | 📋 Ready |
| Notch Pay | payment | 🇨🇲 🇨🇮 🇸🇳 +3 | 31 | 📋 Ready |
| Orange Money Mali | payment | 🇲🇱 | 2 | 📋 Ready |
| Wave | payment | 🇸🇳 🇨🇮 🇲🇱 +8 | 12 | 📋 Ready |
| <!-- fin du tableau --> |
Legend: ✅ AI Ready = all capabilities verified · X verified · Y ready = awaiting production validation · 📋 Ready = spec validated · 🗓 Planned = specs coming soon
Use with an MCP client
Claude Code
claude mcp add --transport http afrotools https://mcp.afro.tools/mcp
Cursor / Windsurf / VS Code Copilot
{
"mcpServers": {
"afrotools": {
"type": "http",
"url": "https://mcp.afro.tools/mcp"
}
}
}
Claude Code plugin
/plugin marketplace add afrotools/afrotools
/plugin install afrotools
Auto-activated skills based on context:
payment— integrating a payment APIsms— integrating an SMS APIdebug— when an integration based on an afrotools spec fails → diagnoses whether the problem is a spec error, a missing gotcha, or an undocumented API change
Manual commands:
/afrotools:spec <provider> <capability>— inspect a full spec/afrotools:list— list all available specs/afrotools:new <category> <provider> <capability>— scaffold a new spec
Contributing
See CONTRIBUTING.md to add a spec or improve an existing one.
Spec lifecycle: draft → ready → verified
A provider earns the AI Ready badge when all its capabilities reach verified.
License
Apache 2.0 — see 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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.