mcpField
W
wegene-assistant MCP server

wegene-assistant MCP server

Local
github.com/xraywuAI & Agents4Updated 90w ago
Repository

About wegene-assistant MCP server

wegene-assistant MCP server lets WeGene users make their genetic test reports available to an LLM for analysis. It provides account authorization and tools for finding and reading profiles and reports.

Key features

  1. 01Authorize access through WeGene Open API
  2. 02List account profiles
  3. 03Inspect available report metadata
  4. 04Retrieve individual report results
  5. 05Expose reports as JSON resources

Use cases

  1. 01Analyze genetic testing reports with an LLM
  2. 02Find reports associated with a WeGene profile

MCP support

The MCP server exposes authorized WeGene reports as resources and provides tools to authorize, list profiles, inspect report metadata, and retrieve report results.

#wegene-assistant#genetic-analysis#health-tech

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "wegene-assistant": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli"
      ]
    }
  }
}
Run commandnpx -y @smithery/cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@smithery/cli

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

wegene-assistant MCP server

smithery badge

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
  1. Clone this project
  2. 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"
      ]
    }
  }
}

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.