Scholar runs on your own machine — the client starts it, so there is no endpoint to ping. 72 installs a week from pypi. Last commit 5 May 2026.
Hardened Scholar MCP for deep academic research (Scopus, OpenAlex, Unpaywall) with PDF vision.
Nothing serious here today
Today is the operative word: we check Scholar every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add scholar -e 'SCOPUS_API_KEY=<SCOPUS_API_KEY>' -e 'CONTACT_EMAIL=<CONTACT_EMAIL>' -- uvx scholar-academic-mcp{
"mcpServers": {
"scholar": {
"command": "uvx",
"args": [
"scholar-academic-mcp"
],
"env": {
"CONTACT_EMAIL": "<CONTACT_EMAIL>",
"SCOPUS_API_KEY": "<SCOPUS_API_KEY>"
}
}
}
}[mcp_servers.scholar]
command = "uvx"
args = ["scholar-academic-mcp"]
env = { SCOPUS_API_KEY = "<SCOPUS_API_KEY>", CONTACT_EMAIL = "<CONTACT_EMAIL>" }{
"mcpServers": {
"scholar": {
"command": "uvx",
"args": [
"scholar-academic-mcp"
],
"env": {
"CONTACT_EMAIL": "<CONTACT_EMAIL>",
"SCOPUS_API_KEY": "<SCOPUS_API_KEY>"
}
}
}
}{
"servers": {
"scholar": {
"type": "stdio",
"command": "uvx",
"args": [
"scholar-academic-mcp"
],
"env": {
"CONTACT_EMAIL": "<CONTACT_EMAIL>",
"SCOPUS_API_KEY": "<SCOPUS_API_KEY>"
}
}
}
}Put your own values in place of
<SCOPUS_API_KEY> (Your Elsevier Scopus API Key), <CONTACT_EMAIL> (Email for OpenAlex polite pool and Unpaywall identification).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
SCOPUS_INST_TOKEN (Optional Elsevier Institutional Token).
Alternatives to Scholar
same job, measured the same wayMCP RAG: index PDFs, repos, YouTube, Discord, text; optional YouTube vision; query with citations.
Token-efficient MCP server for codebase search, NuGet decompilation, and deep PDF reading.
Deep Research MCP for multi-round investigations, traceable evidence, and cited reports.
Budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness.
Arachne MCP — scraping, browser, vision, OCR, RAG, Social Research, GitHub + VRT (56 tools).
Code mode for MCP: search, describe and execute over all your servers, with a sandbox and approvals.
Autonomous deep research reports merging PSFK trend graphs with citable sources.
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.
Scholar — questions
Answers built from our own checks of this server.