Aurora-MCP

Multi-source bioinformatics knowledge base and MCP server integrating plant–compound–mitochondrial data for Aurora ETL.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ndaniel-aurora-mcp": {
      "command": "uvicorn",
      "args": [
        "mcp_server.server:app",
        "--host",
        "0.0.0.0",
        "--port",
        "7860"
      ]
    }
  }
}

Aurora-MCP is a Python-based Model Context Protocol (MCP) server that exposes fast, queryable access to plant-derived molecules and mitochondrial Complex I inhibitors. It lets you connect an MCP client to a local FastAPI service so you can search, link, and reason over curated botanical and biochemical data in conversational workflows.

How to use

You run the MCP server locally and connect your MCP client to it to perform semantic queries across datasets. You can start by launching the server, then use a client to invoke available tools such as listing files and reading text to experiment with the data-backed endpoints. The server exposes a /mcp streaming endpoint for MCP-enabled clients and a /healthz route for quick status checks.

How to install

Prerequisites: you need Python 3.8+ and a working network environment. Prepare a clean Python environment and install dependencies, then start the MCP server.

# 1. Create a clean environment
python3 -m venv .venv
source .venv/bin/activate

# 2. Install dependencies
pip install -r requirements.txt

# 3. Start the MCP server (see the start command below)
uvicorn mcp_server.server:app --host 0.0.0.0 --port 7860

Configuration and run details

The MCP server is designed to run with a FastAPI-based entrypoint. The recommended start command, as shown in the setup, is the following command sequence used to launch the server directly from the project:

{
  "type": "stdio",
  "name": "aurora_mcp",
  "command": "uvicorn",
  "args": ["mcp_server.server:app", "--host", "0.0.0.0", "--port", "7860"]
}

Available tools

list_files

List directory contents via the MCP tool interface for quick data inspection.

read_text

Read a file’s contents as plain text through the MCP tool interface for sample data access.