Skip to content
Back to search

mcp-scholarly

A MCP server to search for accurate academic articles.

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/adityak74--mcp-scholarly/badge.svg)](/listings/adityak74--mcp-scholarly)

HTML

<a href="/listings/adityak74--mcp-scholarly"><img src="/api/listings/adityak74--mcp-scholarly/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.

Install

Claude Desktop

On MacOS: `~/Library/Application\ Support/Claude/claude_desktop_config.json` On Windows: `%APPDATA%/Claude/claude_desktop_config.json`

<details> <summary>Development/Unpublished Servers Configuration</summary>

  "mcpServers": {
    "mcp-scholarly": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly",
        "run",
        "mcp-scholarly"
      ]
    }
  }

</details>

<details> <summary>Published Servers Configuration</summary>

  "mcpServers": {
    "mcp-scholarly": {
      "command": "uvx",
      "args": [
        "mcp-scholarly"
      ]
    }
  }

</details>

or if you are using Docker

<details> <summary>Published Docker Servers Configuration</summary>

  "mcpServers": {
    "mcp-scholarly": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "mcp/scholarly"
      ]
    }
  }

</details>

Installing via Smithery

To install mcp-scholarly for Claude Desktop automatically via [Smithery](https://smithery.ai/server/mcp-scholarly):

npx -y @smithery/cli install mcp-scholarly --client claude

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 · 178 lines

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

  1. [![MseeP.ai Security Assessment Badge](https://mseep.net/pr/adityak74-mcp-scholarly-badge.png)](https://mseep.ai/app/adityak74-mcp-scholarly)
  2. # mcp-scholarly MCP server
  3. [![smithery badge](https://smithery.ai/badge/mcp-scholarly)](https://smithery.ai/server/mcp-scholarly)
  4. A MCP server to search for accurate academic articles. More scholarly vendors will be added soon.
  5. ## Search tools
  6. - `search-arxiv` — arXiv search (no key needed)
  7. - `search-google-scholar` — Google Scholar via the `scholarly` library (free proxy pool)
  8. - `search-google-web` — Google web search via the [SerpBase API](https://serpbase.dev). Optional; only registered when `SERPBASE_API_KEY` is set. Get a key at https://serpbase.dev/dashboard/api-keys (free tier available).
  9. ![demo1.jpeg](examples/demo1.png)
  10. ![image](https://github.com/user-attachments/assets/13202184-bc12-4530-b7c1-2ee698f3e1cc)
  11. <a href="https://glama.ai/mcp/servers/aq05b2p0ql"><img width="380" height="200" src="https://glama.ai/mcp/servers/aq05b2p0ql/badge" alt="Scholarly Server MCP server" /></a>
  12. ![star-history-202551](https://github.com/user-attachments/assets/f22d5796-017c-4c53-b230-101a09a28118)
  13. ## Components
  14. ### Tools
  15. The server implements one tool:
  16. - search-arxiv: Search arxiv for articles related to the given keyword.
  17. - Takes "keyword" as required string arguments
  18. ## Quickstart
  19. ### Install
  20. #### Claude Desktop
  21. On MacOS: `~/Library/Application\ Support/Claude/claude_desktop_config.json`
  22. On Windows: `%APPDATA%/Claude/claude_desktop_config.json`
  23. <details>
  24. <summary>Development/Unpublished Servers Configuration</summary>
  25. ```
  26. "mcpServers": {
  27. "mcp-scholarly": {
  28. "command": "uv",
  29. "args": [
  30. "--directory",
  31. "/Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly",
  32. "run",
  33. "mcp-scholarly"
  34. ]
  35. }
  36. }
  37. ```
  38. </details>
  39. <details>
  40. <summary>Published Servers Configuration</summary>
  41. ```
  42. "mcpServers": {
  43. "mcp-scholarly": {
  44. "command": "uvx",
  45. "args": [
  46. "mcp-scholarly"
  47. ]
  48. }
  49. }
  50. ```
  51. </details>
  52. or if you are using Docker
  53. <details>
  54. <summary>Published Docker Servers Configuration</summary>
  55. ```
  56. "mcpServers": {
  57. "mcp-scholarly": {
  58. "command": "docker",
  59. "args": [
  60. "run", "--rm", "-i",
  61. "mcp/scholarly"
  62. ]
  63. }
  64. }
  65. ```
  66. </details>
  67. ### Installing via Smithery
  68. To install mcp-scholarly for Claude Desktop automatically via [Smithery](https://smithery.ai/server/mcp-scholarly):
  69. ```bash
  70. npx -y @smithery/cli install mcp-scholarly --client claude
  71. ```
  72. ## Development
  73. ### Building and Publishing
  74. To prepare the package for distribution:
  75. 1. Sync dependencies and update lockfile:
  76. ```bash
  77. uv sync
  78. ```
  79. 2. Build package distributions:
  80. ```bash
  81. uv build
  82. ```
  83. This will create source and wheel distributions in the `dist/` directory.
  84. 3. Publish to PyPI:
  85. ```bash
  86. uv publish
  87. ```
  88. Note: You'll need to set PyPI credentials via environment variables or command flags:
  89. - Token: `--token` or `UV_PUBLISH_TOKEN`
  90. - Or username/password: `--username`/`UV_PUBLISH_USERNAME` and `--password`/`UV_PUBLISH_PASSWORD`
  91. ### Debugging
  92. Since MCP servers run over stdio, debugging can be challenging. For the best debugging
  93. experience, we strongly recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector).
  94. You can launch the MCP Inspector via [`npm`](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) with this command:
  95. ```bash
  96. npx @modelcontextprotocol/inspector uv --directory /Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly run mcp-scholarly
  97. ```
  98. Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
  99. ## Using with zorp
  100. [zorp](https://github.com/aviskaar/zorp) needs a search-capable MCP tool
  101. before `validate` will run. This server satisfies that check, because zorp
  102. matches on a search verb in the tool name and these tools are called
  103. `search-arxiv` and `search-google-scholar`.
  104. ```bash
  105. zorp-agent --yes \
  106. --mcp "stdio:scholarly:uv:run:mcp-scholarly" \
  107. validate "<your research question>"
  108. ```
  109. Or configure it once, so every run picks it up:
  110. ```toml
  111. # .zorp/mcp.toml
  112. [[server]]
  113. name = "scholarly"
  114. transport = "stdio"
  115. command = "uv"
  116. args = ["run", "mcp-scholarly"]
  117. trust = "sandbox"
  118. timeout_secs = 60
  119. ```
  120. Notes measured against zorp's transport, not assumed:
  121. - `search-arxiv` answers in about 1 second. zorp's default stdio read
  122. budget is 30 seconds, so the default is comfortable. `timeout_secs = 60`
  123. above is headroom for `search-google-scholar`, which goes through
  124. `scholarly` and a free proxy pool and is far less predictable.
  125. - Logging goes to stderr. Nothing but JSON-RPC reaches stdout, which is
  126. what zorp's newline-delimited framing requires.
  127. - An empty keyword comes back as an MCP tool error rather than an empty
  128. result set. zorp cares about that distinction: a failed search that
  129. looks like "no prior work" would put a wrong novelty score into an
  130. evidence record.
  131. - arxiv returns best-effort matches for any query, including nonsense, so
  132. a non-empty result set is not by itself evidence that prior work exists.
  133. The tool description says so, since that is the text the model reads.

Ratings and comments

Sign in to rate this skill.

Sign in

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