$git clone https://github.com/JackKuo666/Google-Scholar-MCP-Serverπ Enable AI assistants to search and access Google Scholar papers through a simple MCP interface.
| 1 | # Google Scholar MCP Server |
| 2 | [](https://smithery.ai/server/@JackKuo666/google-scholar-mcp-server) |
| 3 | Β |
| 4 | π Enable AI assistants to search and access Google Scholar papers through a simple MCP interface. |
| 5 | Β |
| 6 | The Google Scholar MCP Server provides a bridge between AI assistants and Google Scholar through the Model Context Protocol (MCP). It allows AI models to search for academic papers and access their content in a programmatic way. |
| 7 | Β |
| 8 | ## β¨ Core Features |
| 9 | - π Paper Search: Query Google Scholar papers with custom search strings or advanced search parameters β |
| 10 | - π Efficient Retrieval: Fast access to paper metadata β |
| 11 | - π€ Author Information: Retrieve detailed information about authors β |
| 12 | - π Research Support: Facilitate academic research and analysis β |
| 13 | Β |
| 14 | ## π Quick Start |
| 15 | Β |
| 16 | ### Installing Manually |
| 17 | ### Installing via Smithery |
| 18 | Β |
| 19 | To install google-scholar Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@JackKuo666/google-scholar-mcp-server): |
| 20 | Β |
| 21 | #### claude |
| 22 | Β |
| 23 | ```sh |
| 24 | npx -y @smithery/cli@latest install @JackKuo666/google-scholar-mcp-server --client claude --config "{}" |
| 25 | ``` |
| 26 | Β |
| 27 | #### Cursor |
| 28 | Β |
| 29 | Paste the following into Settings β Cursor Settings β MCP β Add new server: |
| 30 | - Mac/Linux |
| 31 | ```s |
| 32 | npx -y @smithery/cli@latest run @JackKuo666/google-scholar-mcp-server --client cursor --config "{}" |
| 33 | ``` |
| 34 | #### Windsurf |
| 35 | ```sh |
| 36 | npx -y @smithery/cli@latest install @JackKuo666/google-scholar-mcp-server --client windsurf --config "{}" |
| 37 | ``` |
| 38 | ### CLine |
| 39 | ```sh |
| 40 | npx -y @smithery/cli@latest install @JackKuo666/google-scholar-mcp-server --client cline --config "{}" |
| 41 | ``` |
| 42 | Β |
| 43 | 1. Clone the repository: |
| 44 | ``` |
| 45 | git clone https://github.com/JackKuo666/google-scholar-MCP-Server.git |
| 46 | cd google-scholar-MCP-Server |
| 47 | ``` |
| 48 | Β |
| 49 | 2. Install the required dependencies: |
| 50 | ``` |
| 51 | pip install -r requirements.txt |
| 52 | ``` |
| 53 | Β |
| 54 | Β |
| 55 | For development: |
| 56 | Β |
| 57 | ```bash |
| 58 | # Clone and set up development environment |
| 59 | git clone https://github.com/JackKuo666/Google-Scholar-MCP-Server.git |
| 60 | cd Google-Scholar-MCP-Server |
| 61 | Β |
| 62 | # Create and activate virtual environment |
| 63 | python -m venv venv |
| 64 | source venv/bin/activate # On Windows use `venv\Scripts\activate` |
| 65 | Β |
| 66 | # Install dependencies |
| 67 | pip install -r requirements.txt |
| 68 | ``` |
| 69 | Β |
| 70 | ## π Usage |
| 71 | Β |
| 72 | Start the MCP server: |
| 73 | Β |
| 74 | ```bash |
| 75 | python google_scholar_server.py |
| 76 | ``` |
| 77 | Β |
| 78 | Once the server is running, you can use the provided MCP tools in your AI assistant or application. Here are some examples of how to use the tools: |
| 79 | Β |
| 80 | ### Example 1: Search for papers using keywords |
| 81 | Β |
| 82 | ```python |
| 83 | result = await mcp.use_tool("search_google_scholar_key_words", { |
| 84 | "query": "artificial intelligence ethics", |
| 85 | "num_results": 5 |
| 86 | }) |
| 87 | print(result) |
| 88 | ``` |
| 89 | Β |
| 90 | ### Example 2: Perform an advanced search |
| 91 | Β |
| 92 | ```python |
| 93 | result = await mcp.use_tool("search_google_scholar_advanced", { |
| 94 | "query": "machine learning", |
| 95 | "author": "Hinton", |
| 96 | "year_range": [2020, 2023], |
| 97 | "num_results": 3 |
| 98 | }) |
| 99 | print(result) |
| 100 | ``` |
| 101 | Β |
| 102 | ### Example 3: Get author information |
| 103 | Β |
| 104 | ```python |
| 105 | result = await mcp.use_tool("get_author_info", { |
| 106 | "author_name": "Geoffrey Hinton" |
| 107 | }) |
| 108 | print(result) |
| 109 | ``` |
| 110 | Β |
| 111 | These examples demonstrate how to use the three main tools provided by the Google Scholar MCP Server. Adjust the parameters as needed for your specific use case. |
| 112 | Β |
| 113 | ## Usage with Claude Desktop |
| 114 | Β |
| 115 | Add this configuration to your `claude_desktop_config.json`: |
| 116 | Β |
| 117 | (Mac OS) |
| 118 | Β |
| 119 | ```json |
| 120 | { |
| 121 | "mcpServers": { |
| 122 | "google-scholar": { |
| 123 | "command": "python", |
| 124 | "args": ["-m", "google_scholar_mcp_server"] |
| 125 | } |
| 126 | } |
| 127 | } |
| 128 | ``` |
| 129 | Β |
| 130 | (Windows version): |
| 131 | Β |
| 132 | ```json |
| 133 | { |
| 134 | "mcpServers": { |
| 135 | "google-scholar": { |
| 136 | "command": "C:\\Users\\YOUR\\PATH\\miniconda3\\envs\\mcp_server\\python.exe", |
| 137 | "args": [ |
| 138 | "D:\\code\\YOUR\\PATH\\Google-Scholar-MCP-Server\\google_scholar_server.py" |
| 139 | ], |
| 140 | "env": {}, |
| 141 | "disabled": false, |
| 142 | "autoApprove": [] |
| 143 | } |
| 144 | } |
| 145 | } |
| 146 | ``` |
| 147 | Using with Cline |
| 148 | ```json |
| 149 | { |
| 150 | "mcpServers": { |
| 151 | "google-scholar": { |
| 152 | "command": "bash", |
| 153 | "args": [ |
| 154 | "-c", |
| 155 | "source /home/YO |