Generate Hypothesis

基于MCP协议的AI研究论文生成工具 - AstroInsight Research Assistant。专为科研工作者设计，提供智能论文检索、事实信息提取、研究假设生成等完整研究流程。

python

GitHub Stars

python

Language

4 months ago

First Indexed

3 weeks 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": {
    "daiduo2-generate-hypothesis-mcp": {
      "command": "python",
      "args": [
        "astroinsight_optimized_fastmcp.py"
      ],
      "env": {
        "QWEN_API_TOKEN": "YOUR_QWEN_API_TOKEN",
        "MINERU_API_TOKEN": "YOUR_MINERU_API_TOKEN",
        "DEEPSEEK_API_TOKEN": "YOUR_DEEPSEEK_API_TOKEN"
      }
    }
  }
}

Generate Hypothesis MCP is an MCP-enabled AI research assistant that automates the end-to-end workflow from keyword search to automated research hypothesis generation. It integrates multiple AI models to help researchers retrieve papers, extract key facts, generate novel hypotheses, and optimize technical approaches, all through a consistent MCP interface.

How to use

You interact with the server through an MCP client to start and monitor tasks. Use the available MCP functions to launch an automated research paper workflow, check progress, and see results.

Key capabilities you can leverage:

generate_research_paper: start a full paper generation process by providing keywords and the number of papers to search.
get_task_status: query the status and progress of an ongoing task.
list_active_tasks: view an overview of current and recent tasks.

How to install

Prerequisites you need before running the MCP server.

# Ensure you have Python 3.8 or newer
python --version

# Set up a virtual environment (optional but recommended)
python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`

# Install required Python dependencies
pip install -r requirements.txt

Next, prepare environment variables required by the server.

cp .env.example .env

# Populate your API tokens
DEEPSEEK_API_TOKEN=your_deepseek_token
QWEN_API_TOKEN=your_qwen_token
MINERU_API_TOKEN=your_mineru_token

Start the MCP server to begin accepting MCP client requests.

python astroinsight_optimized_fastmcp.py

Additional notes

The server exposes three MCP functions you can call from any compatible MCP client. Environment variables shown above must be set for the server to access external AI and data sources.

Available tools

generate_research_paper

Launches the full research paper generation workflow by supplying keywords and the number of papers to search.

get_task_status

Retrieves detailed status, progress, and results for a specific task.

list_active_tasks

Provides an overview of all active and recently completed tasks.

Built by

VeilStrat

AI signals for GTM teams