Data · Local MCP server
Scholar MCP
Federated academic search, citation traversal, persistent PDF download, and temporary reading.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.Liyux3/scholar-mcp- Version
- 0.8.4
- Status
- Active
- Category
- data
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-09-05
- Updated
- 2026-09-05
- Publisher
- Liyux3 (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/Liyux3) · how
- Listed under
- PDF MCP servers
- Repository
- github.com/Liyux3/scholar-mcp
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPIruntime: uvx | scholar-mcp | 0.8.4 | stdio |
How to connect Scholar MCP
Scholar MCP runs locally from a Python package published to PyPI: scholar-mcp version 0.8.4. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx scholar-mcp. It reads these environment variables: SCHOLAR_DATA_DIR, SCHOLAR_MCP_EXTENSIONS, S2_API_KEY (secret), OPENALEX_API_KEY (secret), CORE_API_KEY (secret), SCOPUS_API_KEY (secret), DASHSCOPE_API_KEY (secret), EXA_API_KEY (secret), ZOTERO_API_KEY (secret), ZOTERO_LIBRARY_ID, NOTION_API_KEY (secret) and NOTION_DATA_SOURCE_ID; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"scholar-mcp": {
"command": "uvx",
"args": [
"scholar-mcp"
],
"env": {
"SCHOLAR_DATA_DIR": "<value>",
"SCHOLAR_MCP_EXTENSIONS": "<value>",
"S2_API_KEY": "<secret>",
"OPENALEX_API_KEY": "<secret>",
"CORE_API_KEY": "<secret>",
"SCOPUS_API_KEY": "<secret>",
"DASHSCOPE_API_KEY": "<secret>",
"EXA_API_KEY": "<secret>",
"ZOTERO_API_KEY": "<secret>",
"ZOTERO_LIBRARY_ID": "<value>",
"NOTION_API_KEY": "<secret>",
"NOTION_DATA_SOURCE_ID": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More data servers
| Server | Runs |
|---|---|
| SchedulalaSchedule and publish social posts to 12 platforms with first comments, analytics, and listening. | Remote & Local · HTTP, stdioLive check: sign-in required |
| Schelling Add ForwardCommunication and persistent state for AI agents: spaces, posts, search, mailbox, direct messages. | Remote & Local · HTTP, stdioLive check: ✓ handshake |
| ScholarHardened Scholar MCP for deep academic research (Scopus, OpenAlex, Unpaywall) with PDF vision. | Local · stdio |
| Scholar FeedRank CS/AI/ML papers by citations, forecast impact, or code adoption; trace 23.2M citation edges. | Remote & Local · HTTP, stdioLive check: ✓ handshake |
| Scholar MCPFastMCP server for scholarly papers, patents, books and standards with docling PDF conversion. | Local · stdio, HTTP |
| Scholar RAG MCPAcademic paper knowledge-base MCP server: PDF ingest, vector search with reranking, KB management. | Local · stdio |
| Scholar SidekickCatch AI-fabricated citations (real DOI + fake title). Retraction, open-access, 10,000+ CSL styles. | Remote & Local · HTTP, stdioLive check: ✓ handshake |
| ScholarFetchMulti-engine scholarly research server for search, traversal, full text, and reading lists. | Remote · HTTPLive check: ✓ handshake |