> ## Documentation Index
> Fetch the complete documentation index at: https://developer.eka.care/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP for EMR

> Self-hosted MCP server bridging Eka.care APIs with LLM applications

## Core Functionality

A **self-hosted Model Context Protocol (MCP) server** that bridges **Eka.care healthcare APIs** with LLM-powered applications, enabling AI assistants to securely interact with clinical and operational data.

Read more : ([API Reference - MCP for EMR](/ai-tools/mcp-server/introduction)) section.

### Supported Capabilities

AI assistants can:

* **Manage appointments**
  * Create, update, and retrieve patient appointments
* **Access patient records**
  * Search, create, retrieve, and update patients within a workspace
* **Manage doctor and clinic data**
  * Access doctor profiles and clinic information

***

### Coming Soon

Planned extensions to expand clinical workflows:

* **Handle prescriptions**
  * Generate and manage digital prescriptions
* **Get prescription history**
  * Retrieve patient medication history
* **Process assessments**
  * Handle and analyze self-assessment data

***

## Key Capabilities

* **Three usage modes**
  * MCP server
  * Direct async Python library
  * Sync wrapper (CrewAI-compatible)
* **Modular architecture**
  * Easily extend with new Eka.care API modules
* **Authentication**
  * Client ID / Client Secret with JWT token management for local connections
  * OIDC flow for remote server deployments
  * Optional API key support
* **LLM-optimized**
  * Structured, predictable responses designed for AI consumption
* **Error transparency**
  * Eka.care API errors are forwarded directly for easier debugging

***

## Limits

* **Python version**
  * Requires **Python ≥ 3.10**
* **Self-hosted only**
  * Designed for organizational and controlled deployments
* **API-dependent**
  * All functionality requires valid **Eka.care API credentials**

***

## Dependencies

Core dependencies required to run the MCP server:

```bash theme={null}
FastMCP          # MCP protocol implementation (git main branch)
httpx            # Async HTTP client for API calls
pydantic         # Data validation and settings management
PyJWT            # Authentication token handling
py-key-value-aio # Redis-based async storage for auth tokens
python-dotenv    # Environment configuration
```

***

Read more : ([API Reference - MCP for EMR](/ai-tools/mcp-server/introduction)) section.