Scholar runs on your own machine — the client starts it, so there is no endpoint to ping. 47 installs a week from pypi. Last commit 5 May 2026.
Hardened Scholar MCP for deep academic research (Scopus, OpenAlex, Unpaywall) with PDF vision.
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.
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 -- uvx scholar-academic-mcp
{
"mcpServers": {
"scholar": {
"args": [
"scholar-academic-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.scholar]
command = "uvx"
args = ["scholar-academic-mcp"]
{
"mcpServers": {
"scholar": {
"args": [
"scholar-academic-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"scholar": {
"args": [
"scholar-academic-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
SCOPUS_API_KEY (Your Elsevier Scopus API Key), CONTACT_EMAIL (Email for OpenAlex polite pool and Unpaywall identification), SCOPUS_INST_TOKEN (Optional Elsevier Institutional Token).
The author declared them in the registry entry; get the values from the project itself.
MCP RAG: index PDFs, repos, YouTube, Discord, text; optional YouTube vision; query with citations.
Budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness.
The open retrieval layer for AI agents — index code, docs, data. Search via MCP.
Arachne MCP — scraping, browser, vision, OCR, RAG, Social Research, GitHub + VRT (56 tools).
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.
PDF parsing server with text extraction, metadata, search, images, and TOC via MCP
MCP server for the OpenAI ChatGPT API — chat, vision, and embeddings
Answers built from our own checks of this server.