Research Gap Analyzer MCP Server

An AI-powered Research Copilot that automates literature review, research gap detection, and novelty evaluation.

Features (9 Tools)

1. search_literature(topic): Search recent papers across arXiv and Semantic Scholar.
2. summarize_literature(topic): Extract methods, datasets, and limitations from literature.
3. find_gaps(topic): Identify overlooked research areas.
4. generate_ideas(topic): Propose novel FYP/research ideas.
5. find_datasets(topic): Extract dataset names, modalities, and usage details.
6. evaluate_novelty(idea): Semantic novelty score (0-10) using BGE embeddings.
7. suggest_venues(idea): Recommend target journals and conferences.
8. suggest_experiments(idea): Design experiments and suggest metrics.
9. create_literature_review(topic): Compile structured literature reviews.

Installation

1. Clone & Setup

# Install dependencies
uv sync

2. Configure Environment

Create a .env file:

GROQ_API_KEY=your_groq_key_here
GEMINI_API_KEY=your_gemini_key_here
SEMANTIC_SCHOLAR_API_KEY=optional_key_here

3. Usage

Run the server locally:

uv run main.py

Remote Deployment (fastmcp.cloud)

Deploy to FastMCP Cloud

1. Push your code to GitHub
2. Go to fastmcp.cloud
3. Connect your GitHub repository
4. Configure environment variables in the fastmcp.cloud dashboard:
   • GROQ_API_KEY
   • GEMINI_API_KEY
   • SEMANTIC_SCHOLAR_API_KEY (optional)
5. Deploy - the platform will automatically detect and run your MCP server

Remote Claude Desktop Configuration

After deployment, update your claude_desktop_config.json to use the remote server:

{
  "mcpServers": {
    "research_analyzer": {
      "url": "https://your-server-name.fastmcp.cloud"
    }
  }
}

Replace your-server-name with your actual fastmcp.cloud server URL.

Claude Desktop Configuration

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "research_analyzer": {
      "command": "uv",
      "args": [
        "--directory",
        "[YOUR_PROJECT_PATH]/research-gap-analyzer",
        "run",
        "main.py"
      ]
    }
  }
}

Tech Stack

• Framework: FastMCP
• LLM: Groq (Llama 3.3 70B) & Google Gemini 2.0 Flash
• Search: arXiv API, Semantic Scholar API
• Embeddings: Sentence-Transformers (BAAI/bge-small-en-v1.5)