wegene-assistant MCP server

By xraywu GitHub

MCP server to analyze your genetic test results from WeGene

wegene-assistant genetic-analysis

Overview

what is WeGene Assistant?

WeGene Assistant is an MCP server designed to analyze genetic test results from WeGene, utilizing a large language model (LLM) to interpret user reports.

how to use WeGene Assistant?

To use WeGene Assistant, users must authorize their WeGene account, after which they can access their genetic reports through a custom URI scheme and various API tools provided by the server.

key features of WeGene Assistant?

Integration with WeGene's Open API for seamless report access
Custom URI scheme for easy report retrieval
Multiple tools for user authorization and report management

use cases of WeGene Assistant?

Analyzing genetic test results for health insights
Accessing and managing multiple genetic profiles
Utilizing LLM for personalized genetic report interpretation

FAQ from WeGene Assistant?

What is required to use WeGene Assistant?

You need a WeGene Open API key/secret and to authorize your account to access reports.

Can I access multiple reports?

Yes! Once authorized, all reports under your account will be available.

Is there a specific installation process?

Yes, you can install via Smithery or set it up locally by cloning the project and configuring the server.

Content

wegene-assistant MCP server

MCP server for WeGene Assistant, using LLM to analyze a user's WeGene genetic testing report.

Components

Resources

Once a user is authorized, all the reports under his/her account will be exposed as a resource:

Custom wegene:// URI scheme for accessing each individual report
A report resource has a name, description and application/json mimetype

Tools

The server implements one tool:

wegene-oauth: Start a WeGene Open API oAuth process in the browser
- The user should complete the authorization in 120 seconds so LLM will be able to further access the reports.
wegene-get-profiles: Read the profile list under a user's WeGene account
- Profiles' name and id will be returned for LLM to use.
wegene-get-report-info: Return the report meta info so LLM will know what reports are available.
- A list of report names, descriptions, endpoints, etc. will be returned
wegene-get-report: Read the results of a single report under a profile
- Returns the result JSON specified in WeGene's Open API platform
- Arguements
  - report_endpoint: The report's endpoint to be retrieved from
  - report_id: The report's id to be retrieved
  - profile_id: The profile id to retrieve report from

Configuration

You will need WeGene Open API key/secret to use this project.
Copy .env.example as .env and update the key and secret in the file.

Quickstart

Install

Installing via Smithery

To install WeGene Assistant for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @xraywu/mcp-wegene-assistant --client claude

Insall Locally

Prepare MCP Server

Clone this project
Run uv sync --dev --all-extras under the project's root folder

Claude Desktop Configuration

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

Add below contents in the configuration file:

{
  "mcpServers": {
    "wegene-assistant": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/wegene-assistant",
        "run",
        "wegene-assistant"
      ]
    }
  }
}

No tools information available.

No content found.