Keka MCP Server
Integrates with Keka HR platform to manage employee profiles, attendance, leave applications, payslips, and holidays through OAuth2-authenticated API tools.
README
Keka MCP Server
A Model Context Protocol (MCP) server for integrating with the Keka HR platform. This server exposes Keka employee management, attendance, leave, payslip, and holiday APIs as MCP tools, with robust OAuth2 authentication and modular code structure.
Features
- OAuth2 Authentication: Securely connects to Keka using OAuth2 credentials.
- Tool-based API: Exposes Keka HR features as MCP tools for easy integration and automation.
- Modular Structure: Clean, extensible TypeScript codebase modeled after best practices.
- Docker Support: Ready-to-use Dockerfile for containerized deployment.
Environment Variables
Create a .env file in the project root with the following:
KEKA_CLIENT_ID=your_keka_client_id_here
KEKA_CLIENT_SECRET=your_keka_client_secret_here
KEKA_REFRESH_TOKEN=your_keka_refresh_token_here
# Optional:
KEKA_API_BASE_URL=https://master.kekademo.com/api/v1
Available Tools
1. keka_get_employee_profile
Get detailed profile information for a specific employee.
- Arguments:
employee_id(string, required): The UUID of the employee.
- Example:
{
"employee_id": "EMP123456"
}
2. keka_get_attendance
Get attendance records for an employee within a date range.
- Arguments:
employee_id(string, required)start_date(string, required, format: YYYY-MM-DD)end_date(string, required, format: YYYY-MM-DD)page(number, optional, default: 1)page_size(number, optional, default: 100)
- Example:
{
"employee_id": "EMP123456",
"start_date": "2024-01-01",
"end_date": "2024-01-31",
"page": 1,
"page_size": 50
}
3. keka_apply_leave
Apply for leave for an employee.
- Arguments:
employee_id(string, required)start_date(string, required)end_date(string, required)leave_type(string, required, leave type UUID)reason(string, required)
- Example:
{
"employee_id": "EMP123456",
"start_date": "2024-04-10",
"end_date": "2024-04-12",
"leave_type": "ANNUAL",
"reason": "Family function"
}
4. keka_get_leave_balances
Get a consolidated view of all leave balances for an employee.
- Arguments:
employee_id(string, required)
- Example:
{
"employee_id": "EMP123456"
}
5. keka_get_payslip
Get payslip for an employee for a specific month and year.
- Arguments:
employee_id(string, required)month(string, required, e.g., "4" for April)year(string, required, e.g., "2024")
- Example:
{
"employee_id": "EMP123456",
"month": "4",
"year": "2024"
}
6. keka_get_upcoming_holidays
Get the list of upcoming company holidays.
- Arguments: none
- Example:
{}
7. keka_view_leave_history
View the leave history for an employee.
- Arguments:
employee_id(string, required)start_date(string, optional)end_date(string, optional)status(string, optional)page(number, optional, default: 1)page_size(number, optional, default: 100)
- Example:
{
"employee_id": "EMP123456",
"start_date": "2024-01-01",
"end_date": "2024-04-01",
"status": "APPROVED",
"page": 1,
"page_size": 20
}
8. keka_get_leave_types
Get the list of available leave types.
- Arguments: none
- Example:
{}
Usage
Local (Node.js)
- Install dependencies:
npm install - Build the TypeScript project:
npm run build - Start the MCP server:
node build/index.js
Docker
- Build the Docker image:
docker build -t keka-mcp . - Run the container (using your .env file):
docker run --env-file .env keka-mcp
Project Structure
src/index.ts— Main MCP server implementation, tool definitions, Keka API integration..env— Environment variables for Keka OAuth2 credentials.Dockerfile— Containerization support.package.json— Project dependencies and scripts.
Contributing
Pull requests and issues are welcome! Please ensure any new tools or features follow the modular handler style and include robust error handling.
License
MIT
Reference
This project is generated and maintained with best practices for MCP integrations.
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.
