Semantic Scholar
MCP server by smaniches
Search 200M+ academic papers and explore citations, authors and recommendations through the Semantic Scholar API.
Install Semantic Scholar
Runs on your machine. Your client starts it with this command:
Needs uv (Python) on your computer. The setup steps below show where the command goes in each client.
SEMANTIC_SCHOLAR_API_KEYsecret optional Semantic Scholar API key for higher rate limits (free at semanticscholar.org/product/api)
Share this server
Opens this page, with the install command and setup steps.
mcp.tc/i/semantic-scholarAbout
Connects an assistant to the Semantic Scholar API for academic research. It offers 14 typed tools for paper search, citation graph traversal in both directions, author profiles, recommendations, bulk lookups and full-text snippet search. Paper IDs can be given as Semantic Scholar ID, DOI, ArXiv, PubMed, Corpus ID, ACL or URL.
Runs locally over stdio from the PyPI package s2-mcp-server, started with uvx. It can also be installed with pip or Docker. No API key is needed to start (public limit of 1 request per second). An optional SEMANTIC_SCHOLAR_API_KEY raises the limit to 10 requests per second.
What you can do
- Search papers across the Semantic Scholar index
- Traverse citations and references for a paper
- Look up author profiles
- Get paper recommendations
- Run bulk lookups for up to 500 papers or 1000 authors
- Search full-text snippets with surrounding context
- Return results as Markdown or JSON
Tools
Local servers list their tools once they’re running, so we can’t show them here. Look for the list in its documentation; your client shows them after you add it.
Example prompts
Find recent papers on retrieval-augmented generation and summarize the top five
Show papers that cite the DOI 10.1038/nature14539
Look up the author profile for Yoshua Bengio and list his most cited papers
Recommend papers similar to arXiv 1706.03762
Set up
Every client starts Semantic Scholar on your machine with the same command. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport stdio semantic-scholar --env "SEMANTIC_SCHOLAR_API_KEY=<YOUR_SEMANTIC_SCHOLAR_API_KEY>" -- uvx s2-mcp-server- Start Claude Code and type
/mcp. semantic-scholar should show as connected.
Add --scope user to make it available in every project. Replace the placeholders with your own values.
Claude Desktop
- Open Settings → Developer → Edit Config. It opens
claude_desktop_config.json. Add:
{
"mcpServers": {
"semantic-scholar": {
"command": "uvx",
"args": [
"s2-mcp-server"
],
"env": {
"SEMANTIC_SCHOLAR_API_KEY": "<YOUR_SEMANTIC_SCHOLAR_API_KEY>"
}
}
}
}- Save the file and restart Claude Desktop. Replace the placeholders with your own values.
Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"semantic-scholar": {
"command": "uvx",
"args": [
"s2-mcp-server"
],
"env": {
"SEMANTIC_SCHOLAR_API_KEY": "<YOUR_SEMANTIC_SCHOLAR_API_KEY>"
}
}
}
}Needs uv (Python) on your computer. Replace the placeholders with your own values.
VS Code
Add it to .vscode/mcp.json. VS Code asks for the secret the first time and stores it securely:
{
"servers": {
"semantic-scholar": {
"type": "stdio",
"command": "uvx",
"args": [
"s2-mcp-server"
],
"env": {
"SEMANTIC_SCHOLAR_API_KEY": "${input:semantic-scholar-api-key}"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "semantic-scholar-api-key",
"description": "SEMANTIC_SCHOLAR_API_KEY",
"password": true
}
]
}Needs uv (Python) on your computer.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"semantic-scholar": {
"command": "uvx",
"args": [
"s2-mcp-server"
],
"env": {
"SEMANTIC_SCHOLAR_API_KEY": "<YOUR_SEMANTIC_SCHOLAR_API_KEY>"
}
}
}
}- Refresh the MCP server list in Cascade. Replace the placeholders with your own values.
Devin Desktop is the new name for Windsurf.
Codex
codex mcp add semantic-scholar --env "SEMANTIC_SCHOLAR_API_KEY=<YOUR_SEMANTIC_SCHOLAR_API_KEY>" -- uvx s2-mcp-serverOr edit ~/.codex/config.toml directly:
[mcp_servers.semantic-scholar]
command = "uvx"
args = ["s2-mcp-server"]
env = { SEMANTIC_SCHOLAR_API_KEY = "<YOUR_SEMANTIC_SCHOLAR_API_KEY>" }Needs uv (Python) on your computer. Replace the placeholders with your own values.
Gemini CLI
gemini mcp add -e "SEMANTIC_SCHOLAR_API_KEY=<YOUR_SEMANTIC_SCHOLAR_API_KEY>" semantic-scholar uvx s2-mcp-serverThis adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients that start local servers accept this shape:
{
"mcpServers": {
"semantic-scholar": {
"command": "uvx",
"args": [
"s2-mcp-server"
],
"env": {
"SEMANTIC_SCHOLAR_API_KEY": "<YOUR_SEMANTIC_SCHOLAR_API_KEY>"
}
}
}
}Zed puts servers under context_servers in its settings, with the same command, args and env fields.
Needs uv (Python) on your computer. Replace the placeholders with your own values.
Embed
Show Semantic Scholar in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/semantic-scholar)<a href="https://mcp.tc/i/semantic-scholar"><img src="https://mcp.tc/i/semantic-scholar/badge.svg" alt="Semantic Scholar on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/semantic-scholar.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/semantic-scholar" title="Semantic Scholar on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/semantic-scholar.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Semantic Scholar card to your site.
Add the mcp.tc card for Semantic Scholar, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/semantic-scholar.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="semantic-scholar"><a href="https://mcp.tc/i/semantic-scholar">Semantic Scholar on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/semantic-scholar)
```
Reference: https://mcp.tc/embedChange history
This server runs on your computer, so we follow its PyPI package: each new version shows up here, with edits by its owner.
-
New version 1.7.15 (was 1.7.14). Read from PyPI.
-
New version 1.7.14 (was 1.7.13). Read from PyPI.
-
New version 1.7.13 (was 1.7.12). Read from PyPI.
-
New version 1.7.12 (was 1.7.11). Read from PyPI.
-
New version 1.7.11 (was 1.7.10). Read from PyPI.
-
New version 1.7.10 (was 1.7.9). Read from PyPI.
-
New version 1.7.9 (was 1.7.8). Read from PyPI.
-
New version 1.7.8 (was 1.7.7). Read from PyPI.
-
New version 1.7.7 (was 1.7.6). Read from PyPI.
-
New version 1.7.6 (was 1.7.5). Read from PyPI.
-
Tracking started: version 1.7.5.
FAQ
Can I paste mcp.tc/i/semantic-scholar into my MCP client?
No. Semantic Scholar runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx s2-mcp-server.
Does Semantic Scholar need an API key?
Yes. It reads SEMANTIC_SCHOLAR_API_KEY from its environment, and SEMANTIC_SCHOLAR_API_KEY is a secret. Put the value in your client’s config on your own machine, never in a shared file.
Is Semantic Scholar a remote or a local server?
Local. Your client starts it as a process on your computer with uvx s2-mcp-server, which needs uv (Python).
What can Semantic Scholar do?
You can search papers across the Semantic Scholar index, traverse citations and references for a paper and look up author profiles.
Which clients can use it?
Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.
Does mcp.tc track changes to Semantic Scholar?
Partly. It runs on your computer, so we follow its PyPI package: its History tab shows each new version and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read Semantic Scholar’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with smaniches. This page was built from Semantic Scholar’s public metadata, last checked on 4 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.