Skip to content
Back to search

academic-search-mcp-server

Academic Paper Search MCP Server for Claude Desktop integration. Allows Claude to access data from Semantic Scholar and Crossref.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/afrise--academic-search-mcp-server/badge.svg)](/listings/afrise--academic-search-mcp-server)

HTML

<a href="/listings/afrise--academic-search-mcp-server"><img src="/api/listings/afrise--academic-search-mcp-server/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Installing via Smithery

To install Academic Paper Search Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@afrise/academic-search-mcp-server):

npx -y @smithery/cli install @afrise/academic-search-mcp-server --client claude

***note*** this method is largely untested, as their server seems to be having trouble. you can follow the standalone instructions until smithery gets fixed.

Installing via uv (manual install):

1. Install dependencies:

uv add "mcp[cli]" httpx

2. Set up required API keys in your environment or `.env` file:

#  These are not actually implemented
SEMANTIC_SCHOLAR_API_KEY=your_key_here 
CROSSREF_API_KEY=your_key_here  # Optional but recommended

3. Run the server:

uv run server.py

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 140 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Academic Paper Search MCP Server
  2. [![smithery badge](https://smithery.ai/badge/@afrise/academic-search-mcp-server)](https://smithery.ai/server/@afrise/academic-search-mcp-server)
  3. A [Model Context Protocol (MCP)](https://www.anthropic.com/news/model-context-protocol) server that enables searching and retrieving academic paper information from multiple sources.
  4. The server provides LLMs with:
  5. - Real-time academic paper search functionality
  6. - Access to paper metadata and abstracts
  7. - Ability to retrieve full-text content when available
  8. - Structured data responses following the MCP specification
  9. While primarily designed for integration with Anthropic's Claude Desktop client, the MCP specification allows for potential compatibility with other AI models and clients that support tool/function calling capabilities (e.g. OpenAI's API).
  10. **Note**: This software is under active development. Features and functionality are subject to change.
  11. <a href="https://glama.ai/mcp/servers/kzsu1zzz9j"><img width="380" height="200" src="https://glama.ai/mcp/servers/kzsu1zzz9j/badge" alt="Academic Paper Search Server MCP server" /></a>
  12. ## Features
  13. This server exposes the following tools:
  14. - `search_papers`: Search for academic papers across multiple sources
  15. - Parameters:
  16. - `query` (str): Search query text
  17. - `limit` (int, optional): Maximum number of results to return (default: 10)
  18. - Returns: Formatted string containing paper details
  19. - `fetch_paper_details`: Retrieve detailed information for a specific paper
  20. - Parameters:
  21. - `paper_id` (str): Paper identifier (DOI or Semantic Scholar ID)
  22. - `source` (str, optional): Data source ("crossref" or "semantic_scholar", default: "crossref")
  23. - Returns: Formatted string with comprehensive paper metadata including:
  24. - Title, authors, year, DOI
  25. - Venue, open access status, PDF URL (Semantic Scholar only)
  26. - Abstract and TL;DR summary (when available)
  27. - `search_by_topic`: Search for papers by topic with optional date range filter
  28. - Parameters:
  29. - `topic` (str): Search query text (limited to 300 characters)
  30. - `year_start` (int, optional): Start year for date range
  31. - `year_end` (int, optional): End year for date range
  32. - `limit` (int, optional): Maximum number of results to return (default: 10)
  33. - Returns: Formatted string containing search results including:
  34. - Paper titles, authors, and years
  35. - Abstracts and TL;DR summaries when available
  36. - Venue and open access information
  37. ## Setup
  38. ### Installing via Smithery
  39. To install Academic Paper Search Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@afrise/academic-search-mcp-server):
  40. ```bash
  41. npx -y @smithery/cli install @afrise/academic-search-mcp-server --client claude
  42. ```
  43. ***note*** this method is largely untested, as their server seems to be having trouble. you can follow the standalone instructions until smithery gets fixed.
  44. ### Installing via uv (manual install):
  45. 1. Install dependencies:
  46. ```sh
  47. uv add "mcp[cli]" httpx
  48. ```
  49. 2. Set up required API keys in your environment or `.env` file:
  50. ```sh
  51. # These are not actually implemented
  52. SEMANTIC_SCHOLAR_API_KEY=your_key_here
  53. CROSSREF_API_KEY=your_key_here # Optional but recommended
  54. ```
  55. 3. Run the server:
  56. ```sh
  57. uv run server.py
  58. ```
  59. ## Usage with Claude Desktop
  60. 1. Add the server to your Claude Desktop configuration (`claude_desktop_config.json`):
  61. ```json
  62. {
  63. "mcpServers": {
  64. "academic-search": {
  65. "command": "uv",
  66. "args": ["run ", "/path/to/server/server.py"],
  67. "env": {
  68. "SEMANTIC_SCHOLAR_API_KEY": "your_key_here",
  69. "CROSSREF_API_KEY": "your_key_here"
  70. }
  71. }
  72. }
  73. }
  74. ```
  75. 2. Restart Claude Desktop
  76. ## Development
  77. This server is built using:
  78. - Python MCP SDK
  79. - FastMCP for simplified server implementation
  80. - httpx for API requests
  81. ## API Sources
  82. - Semantic Scholar API
  83. - Crossref API
  84. ## License
  85. This project is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0). This license ensures that:
  86. - You can freely use, modify, and distribute this software
  87. - Any modifications must be open-sourced under the same license
  88. - Anyone providing network services using this software must make the source code available
  89. - Commercial use is allowed, but the software and any derivatives must remain free and open source
  90. See the [LICENSE](LICENSE) file for the full license text.
  91. ## Contributing
  92. Contributions are welcome! Here's how you can help:
  93. 1. Fork the repository
  94. 2. Create a feature branch (`git checkout -b feature/amazing-feature`)
  95. 3. Commit your changes (`git commit -m 'Add amazing feature'`)
  96. 4. Push to the branch (`git push origin feature/amazing-feature`)
  97. 5. Open a Pull Request
  98. Please note:
  99. - Follow the existing code style and conventions
  100. - Add tests for any new functionality
  101. - Update documentation as needed
  102. - Ensure your changes respect the AGPL-3.0 license terms
  103. By contributing to this project, you agree that your contributions will be licensed under the AGPL-3.0 license.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.