Mpesa Daraja MCP
M

Mpesa Daraja MCP

A toolkit for scraping Safaricom Daraja API documentation and providing MCP server integration, including an automated documentation scraper and AI assistant integration service
2.5 points
5.6K

What is the Daraja API MCP Server?

This is a documentation server specifically designed for AI assistants, allowing your AI assistant to instantly access the complete documentation of the Safaricom Daraja API. It's like a smart API documentation library where AI assistants can search, query, and compare different APIs to help you develop Daraja integration applications more quickly.

How to use the Daraja API MCP Server?

You only need to configure it once in a supported IDE (such as Kiro, VSCode, Cursor, etc.). After that, your AI assistant can automatically access all Daraja API documents. It supports one - click deployment with Docker and also supports local installation. After configuration, the AI assistant will provide 6 dedicated tools to help you query API information.

Use cases

Suitable for all developers who need to develop Daraja API integrations, especially: • When you need to quickly find API parameters and example code • When comparing the functional differences between different APIs • When learning new features of the Daraja API • When you need offline access to API documents

Main features

Complete API documentation library
Contains complete documentation for 22 Daraja APIs, covering all categories such as authorization, payment, and transaction management. Each API has detailed parameter descriptions, code examples, and response formats.
Intelligent search function
Supports keyword search and category filtering, allowing you to quickly find the API you need. For example, searching for 'payment' and filtering by the 'core' category will find all core payment APIs.
API comparison tool
Can compare the functional differences of 2 - 4 APIs simultaneously, supporting comparison by specific aspects (such as endpoints, authentication methods) to help you choose the most suitable API.
Classified browsing
APIs are organized into 6 logical categories: core payment, payment processing, transaction management, business operations, advanced features, and professional services, making it easy to find by domain.
One - click Docker deployment
Provides complete Docker support. You can start the service with just a few commands without worrying about environment configuration issues. It supports Windows, macOS, and Linux.
Multi - editor support
Compatible with mainstream IDEs and AI assistant platforms such as Kiro, VSCode, Cursor, Windsurf, Claude Desktop, etc., and the configuration is simple.
Advantages
💡 One - stop documentation access: No need to switch between the browser and the IDE. The AI assistant directly provides accurate information
🚀 Fast response: Localized documentation access is faster and more stable than online search
📚 Complete and accurate: Contains all the details of the official documentation, including images and code examples
🔍 Intelligent search: Supports combined keyword and category search, more efficient than manual searching
🔄 Available offline: The documentation is stored locally and can be used normally even when the network is unstable
🐳 Easy to deploy: Docker support ensures environment consistency and reduces configuration issues
Limitations
📅 Manual running of the crawler is required to get the latest version of the documentation
🔐 A valid Safaricom developer account is required for the first crawl
💾 Local storage space (about 50MB) is needed to store the documentation
⚙️ Basic command - line operation knowledge is required for configuration

How to use

Choose a deployment method
It is recommended to use Docker deployment (the simplest). You can also choose local installation. Make sure Docker or Node.js 18+ is installed.
Configure the editor
Configure the MCP server in the IDE you are using. Here is an example of configuring the Kiro IDE, and other editors are similar.
Start the service
Start the Docker container or the local server to ensure the service is running normally.
Start using
Restart your IDE. The AI assistant can now use 6 dedicated tools to query Daraja API documents.

Usage examples

Case 1: Developing the STK Push payment function
You are developing an e - commerce website that accepts M - Pesa payments and need to understand how to use the STK Push API.
Case 2: Choosing the appropriate payment API
You need to choose a payment API for different scenarios but are not sure which one is the most suitable.
Case 3: Quickly finding API parameters
You are debugging an API call but have forgotten the format requirements of a certain parameter.

Frequently Asked Questions

Do I need a Safaricom developer account to use this server?
Will the documentation data be updated regularly?
Which IDEs and AI assistants are supported?
Which is better, Docker deployment or local installation?
How many resources does the server occupy?
How to verify that the server is working properly?

Related resources

GitHub repository
Project source code, latest version, and issue tracking
Safaricom Daraja official documentation
Official API documentation and developer portal
Model Context Protocol official website
Official documentation and specifications of the MCP protocol
Docker installation guide
Docker installation tutorials for various platforms
Problem feedback and discussion
Report bugs, request features, or participate in discussions

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "daraja-docs": {
      "command": "docker",
      "args": ["exec", "-i", "daraja-mcp-server", "node", "dist/index.js"],
      "disabled": false,
      "autoApprove": [
        "search_daraja_apis",
        "get_daraja_api_doc",
        "list_apis_by_category",
        "get_api_summary",
        "get_server_stats",
        "compare_apis"
      ]
    }
  }
}

{
     "mcpServers": {
       "daraja-docs": {
         "command": "docker",
         "args": ["exec", "-i", "daraja-mcp-server", "node", "dist/index.js"],
         "disabled": false,
         "autoApprove": [
           "search_daraja_apis",
           "get_daraja_api_doc",
           "list_apis_by_category",
           "get_api_summary",
           "get_server_stats",
           "compare_apis"
         ]
       }
     }
   }

{
     "mcpServers": {
       "daraja-docs": {
         "command": "node",
         "args": ["mpesa-daraja-mcp/dist/index.js"],
         "disabled": false,
         "autoApprove": [
           "search_daraja_apis",
           "get_daraja_api_doc",
           "list_apis_by_category",
           "get_api_summary",
           "get_server_stats",
           "compare_apis"
         ]
       }
     }
   }

{
     "mcpServers": {
       "daraja-docs": {
         "command": "docker",
         "args": ["exec", "-i", "daraja-mcp-server", "node", "dist/index.js"]
       }
     }
   }
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
6.6K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
8.9K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
5.8K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
8.1K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
6.0K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
7.9K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
6.5K
4 points
U
Uniprof
Uniprof is a tool that simplifies CPU performance analysis. It supports multiple programming languages and runtimes, does not require code modification or additional dependencies, and can perform one-click performance profiling and hotspot analysis through Docker containers or the host mode.
TypeScript
8.2K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
30.4K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
60.7K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
17.5K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
20.9K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
28.1K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
55.9K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
41.3K
4.8 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
19.4K
4.5 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase