Skip to content
Back to search

scholar-search-mcp

An MCP server for academic paper search that integrates with AI assistants (e.g., Claude Code, Cursor), enabling them to search and retrieve academic paper metadata.

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/silung--scholar-search-mcp/badge.svg)](/listings/silung--scholar-search-mcp)

HTML

<a href="/listings/silung--scholar-search-mcp"><img src="/api/listings/silung--scholar-search-mcp/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.

pip install scholar-search-mcp

> Requires Python 3.10+.

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 · 149 lines

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

  1. # Scholar Search MCP
  2. An MCP server for academic literature workflows in Claude, Cursor, and other MCP clients.
  3. It combines Semantic Scholar and arXiv into one unified toolset, with fast parallel search, normalized outputs, source-aware deduplication, and practical research utilities (citations, references, author graph, recommendations, and arXiv source download).
  4. ---
  5. ## Table of Contents
  6. - [Why this project](#why-this-project)
  7. - [Demo videos](#demo-videos)
  8. - [Install](#install)
  9. - [Quick setup (Claude Desktop / Cursor)](#quick-setup-claude-desktop--cursor)
  10. - [Environment variables](#environment-variables)
  11. - [Tool list](#tool-list)
  12. - [Testing with MCP Inspector](#testing-with-mcp-inspector)
  13. - [Contributing](#contributing)
  14. ---
  15. ## Why this project
  16. Most paper tools force you to choose one source or one API style. `scholar-search-mcp` provides one MCP layer for literature search and graph retrieval:
  17. - **One MCP server, multiple scholarly sources**
  18. - **Free-first defaults** (`arXiv` works without keys)
  19. - **LLM-friendly outputs** for downstream reasoning and agent workflows
  20. - **Practical research actions**, not only search
  21. - **Unified search**: `search_papers` runs Semantic Scholar + arXiv in parallel and deduplicates by normalized title.
  22. - **Research graph tools**: details, citations, references, author profile/papers, and recommendations.
  23. - **Batch + source workflows**: fetch up to 500 papers, and download/extract arXiv LaTeX sources.
  24. - **Operational controls**: built-in caching plus env-based source toggles (enable/disable channels).
  25. - **Source strategy**: built-in Semantic Scholar + arXiv, free-first by default (`arXiv` key-free), optional API key for higher Semantic Scholar limits.
  26. ## Demo videos
  27. Agent writes a survey paper with Scholar Search MCP.
  28. <a href="https://youtu.be/C81rVeznoRY"><img src="./static/scholar_search_demo.jpg" alt="Agent uses Scholar Search MCP to write a survey paper" width="640" style="max-width: 100%; height: auto;"></a>
  29. <br>
  30. ## Install
  31. ```bash
  32. pip install scholar-search-mcp
  33. ```
  34. > Requires Python 3.10+.
  35. ## Quick setup (Claude Desktop / Cursor)
  36. Use the same server command in both clients:
  37. ```json
  38. {
  39. "mcpServers": {
  40. "scholar-search": {
  41. "command": "python",
  42. "args": ["-m", "scholar_search_mcp"],
  43. "env": {
  44. "SCHOLAR_SEARCH_ENABLE_SEMANTIC_SCHOLAR": "true",
  45. "SCHOLAR_SEARCH_ENABLE_ARXIV": "true"
  46. }
  47. }
  48. }
  49. }
  50. ```
  51. `SEMANTIC_SCHOLAR_API_KEY` is optional. Add it only if you want higher Semantic Scholar rate limits:
  52. ```json
  53. {
  54. "mcpServers": {
  55. "scholar-search": {
  56. "command": "python",
  57. "args": ["-m", "scholar_search_mcp"],
  58. "env": {
  59. "SCHOLAR_SEARCH_ENABLE_SEMANTIC_SCHOLAR": "true",
  60. "SCHOLAR_SEARCH_ENABLE_ARXIV": "true",
  61. "SEMANTIC_SCHOLAR_API_KEY": "your-key"
  62. }
  63. }
  64. }
  65. }
  66. ```
  67. Difference:
  68. - **Claude Desktop**: edit local config file directly.
  69. - **Cursor**: add an MCP server in Cursor settings UI (or corresponding settings JSON).
  70. Claude Desktop config file locations:
  71. - **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
  72. - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
  73. - **Linux**: `~/.config/Claude/claude_desktop_config.json`
  74. ## Environment variables
  75. | Variable | Description |
  76. | --- | --- |
  77. | `SEMANTIC_SCHOLAR_API_KEY` | Optional. Increases Semantic Scholar rate limits. |
  78. | `SCHOLAR_SEARCH_ENABLE_SEMANTIC_SCHOLAR` | `true/false`, default `true`. |
  79. | `SCHOLAR_SEARCH_ENABLE_ARXIV` | `true/false`, default `true`. |
  80. | `SCHOLAR_SEARCH_CACHE_DIR` | Optional cache directory path. |
  81. | `SCHOLAR_SEARCH_CACHE_TTL_SECONDS` | Cache TTL in seconds, default `86400`. |
  82. | `SCHOLAR_ARXIV_SOURCE_DIR` | Default parent directory for extracted arXiv sources. |
  83. Example (`arXiv` only):
  84. ```json
  85. {
  86. "SCHOLAR_SEARCH_ENABLE_SEMANTIC_SCHOLAR": "false",
  87. "SCHOLAR_SEARCH_ENABLE_ARXIV": "true"
  88. }
  89. ```
  90. ## Tool list
  91. | Tool | Purpose |
  92. | --- | --- |
  93. | `search_papers` | Search papers with optional `limit`, `fields`, `year`, `venue`. |
  94. | `get_paper_details` | Get one paper by DOI, arXiv ID, S2 ID, or URL. |
  95. | `get_paper_citations` | Get papers that cite a given paper. |
  96. | `get_paper_references` | Get references of a given paper. |
  97. | `get_author_info` | Get an author profile by ID. |
  98. | `get_author_papers` | Get papers by a given author. |
  99. | `get_paper_recommendations` | Get similar paper recommendations. |
  100. | `batch_get_papers` | Batch fetch paper details (up to 500 IDs). |
  101. | `download_arxiv_source` | Download and extract arXiv source bundle (`tar.gz`). |
  102. ## Testing with MCP Inspector
  103. ```bash
  104. npm install -g @modelcontextprotocol/inspector
  105. mcp-inspector python -m scholar_search_mcp
  106. ```
  107. ## Contributing
  108. Issues and PRs are welcome: fork repo, create branch, add validation/tests, and open a PR with clear before/after behavior.
  109. ## References
  110. - [Semantic Scholar API Docs](https://api.semanticscholar.org/api-docs)
  111. - [arXiv API User Manual](https://info.arxiv.org/help/api/user-manual.html)

Ratings and comments

Sign in to rate this skill.

Sign in

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