eka_mcp_server 0.2.0

The official Eka MCP Server for medical science tools curated by eka.care

Eka MCP Server

Overview

Eka Care's Model Context Protocol (MCP) server facilitates interaction with medical knowledge-bases specifically curated for the Indian healthcare context. While advanced models from Claude, OpenAI, and others can perform adequately in medical contexts, their responses often lack grounding in factual information and published references. Additionally, India faces a significant challenge with the absence of centralized repositories for branded medications in the public domain.

The Eka MCP Server addresses these challenges by providing structured access to curated knowledge-bases through specialized tools:

• Indian Drug Discovery and Details: Enables lookup across 500,000+ branded drugs available in India, returning comprehensive metadata including generic composition and manufacturer information to enhance LLM responses.
• Treatment Protocols: Provides contextual access to over 180 treatment protocol documents published by authoritative Indian healthcare institutions such as ICMR and RSSDI.

Key Benefits:

• 🩺 Medical Accuracy: Grounds AI responses in verified healthcare information
• 🔄 Seamless Workflow: Provides critical information without requiring context switching
• 🛡️ Reduced Hallucinations: Relies on curated medical data rather than AI's implicit general knowledge
• 🌐 Open Ecosystem: Integrates with the growing MCP open standard

Get Started

Get your developer key from eka.care

[!NOTE]
To obtain the client-id, and client-token reach out to us on [e-mail]

Installation and Setup for Claude Desktop

1. Install UV - https://docs.astral.sh/uv/getting-started/installation/#installation-methods

2. Install Claude desktop application - https://claude.ai/download

3. Locate the configuration file:

   • macOS: /Library/Application\ Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%/Claude/claude_desktop_config.json

   In case the file does not exist, create a new file named claude_desktop_config.json in the above directory.

4. Modify/Create the configuration file with the following settings:

{
  "mcpServers": {
    "eka-mcp-server": {
      "command": "uvx",
      "args": [
        "eka_mcp_server",
        "--eka-api-host",
        "https://api.eka.care",
        "--client-id",
        "<client_id>",
        "--client-secret",
        "<client_secret>"
      ]
    }
  }
}

5. Replace the placeholder values:
   • <client_id>: Your client ID
   • <client_secret>: Your client secret

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uvx eka_mcp_server --eka-api-host https://api.eka.care --client-id <client_id> --client-secret <client_secret>

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Troubleshooting common issues

spawn uvx ENOENT

This commonly happens when uvx is not installed or the command cannot be discovered.

1. Install uv through this command

curl -LsSf https://astral.sh/uv/install.sh | sh

2. Find the path of our uvx installation

which uvx

The output might be something like this

> /opt/homebrew/bin/uvx

In your config, update the command to the full path of the uvx executable. For example:

{
  "mcpServers": {
    "eka-mcp-server": {
      "command": "/opt/homebrew/bin/uvx",
      "args": [
        "eka_mcp_server",
        "--eka-api-host",
        "https://api.eka.care",
        "--client-id",
        "<client_id>",
        "--client-secret",
        "<client_secret>"
      ]
    } 
  }
}

Tools

EKA MCP server tools are curated by the in-house doctors at eka.care and have been validated on an internal set of questionnaire

Medications tool suite

Indian Drug discovery and details

Tool definition here

https://github.com/eka-care/eka_mcp_server/blob/c59af54ee4f323c2a27b62df06d498e006c60e7f/src/eka_mcp_server/constants.py#L1-L8

Access comprehensive information about drugs from a corpus of drugs based on the drug name or generic composition and filtered further through the drug form and volume.

APIs required for this tool

• https://developer.eka.care/api-reference/eka_mcp/medications/search

Treatment Protocols

Tool definition here

https://github.com/eka-care/eka_mcp_server/blob/14ea2d17ac4d93e619583a4b719a925180d8ff7d/src/eka_assist/mcp_server.py#L128-L174

Standardized guidelines, procedures, and decision pathways for healthcare professionals are published by medical bodies. They serve as comprehensive roadmaps for clinical care, ensuring consistent and evidence-based treatment approaches.

Current Coverage:

• 175 medical conditions/tags
• 180 treatment protocols
• Multiple authoritative publishers

Treatment Protocols Workflow

1. For any given query, the LLM has to decide if the tag is supported or not through this API. During the init of the tool, we fetch the supported conditions.
2. Then, for the given tag, the LLM has to get the publishers that address that tag through this API.
3. Finally, with the tag, publisher and query, we fetch the relevant information from the repository of publishers through this API.

APIs required for this tool

1. http://developer.eka.care/api-reference/eka_mcp/protocols/tags
2. http://developer.eka.care/api-reference/eka_mcp/protocols/publishers_by_tag
3. http://developer.eka.care/api-reference/eka_mcp/protocols/search

Accuracy Disclaimer

The Eka MCP Server provides access to medical knowledge bases and drug information intended to support healthcare professionals in India. While we strive for accuracy and reliability, please note:

• The information provided through this service is for informational purposes only and does not constitute medical advice.
• Healthcare professionals should exercise their own clinical judgment when using this information.
• Drug information and treatment protocols may change over time, and we make reasonable efforts to keep our databases updated.
• We cannot guarantee 100% accuracy or completeness of all information, particularly for newly approved medications or recently updated treatment guidelines.
• Users should verify critical information through official sources before making clinical decisions.
• Our database of protocols is ever growing, but does not ensure completeness.

Eka Care assumes no liability for any errors, omissions, or outcomes resulting from the use of information provided through this service.

Bugs and Issue Reporting

Please report any issues or bugs on the GitHub issue tracker.

FAQ

Q: Can I use this without an eka.care account?

A: No, you need valid API credentials from eka.care to access the medical information.

Q: Is this service free?

A: While the MCP server code is open-source, access to eka.care's APIs requires valid credentials. For the initial few days, we are offering free access to the APIs. However, we will be charging for the API usage in the future.

Q: Which LLMs support MCP natively?

A: Currently, Anthropic's Claude models have native MCP support and also Cursor and Windsurf applications.