Data · Local MCP server

Scholar RAG MCP

Academic paper knowledge-base MCP server: PDF ingest, vector search with reranking, KB management.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.notwhiteblank/scholar-rag-mcp
Version
0.4.0
Status
Active
Category
data
Transport
stdio (local process)
Package
PyPI
Published
2026-09-04
Updated
2026-09-04
Publisher
notwhiteblank (GitHub)
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/notwhiteblank) · how
Listed under
PDF MCP servers
Repository
github.com/notwhiteblank/scholar-rag-mcp
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIscholar-rag-mcp0.4.0stdioSCHOLAR_RAG_DATA_DIR, SCHOLAR_RAG_CHAT_BASE_URL (required), SCHOLAR_RAG_EMBED_BASE_URL (required), SCHOLAR_RAG_RERANK_BASE_URL (required)

How to connect Scholar RAG MCP

Scholar RAG MCP runs locally from a Python package published to PyPI: scholar-rag-mcp version 0.4.0. 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-rag-mcp. It reads these environment variables: SCHOLAR_RAG_DATA_DIR, SCHOLAR_RAG_CHAT_BASE_URL (required), SCHOLAR_RAG_EMBED_BASE_URL (required) and SCHOLAR_RAG_RERANK_BASE_URL (required); 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-rag-mcp": {
      "command": "uvx",
      "args": [
        "scholar-rag-mcp"
      ],
      "env": {
        "SCHOLAR_RAG_DATA_DIR": "<value>",
        "SCHOLAR_RAG_CHAT_BASE_URL": "<value>",
        "SCHOLAR_RAG_EMBED_BASE_URL": "<value>",
        "SCHOLAR_RAG_RERANK_BASE_URL": "<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

All 4,815 →
ServerRunsEndpoint or package
ScholarHardened Scholar MCP for deep academic research (Scopus, OpenAlex, Unpaywall) with PDF vision.Local · stdioPyPI: scholar-academic-mcp
Scholar FeedRank CS/AI/ML papers by citations, forecast impact, or code adoption; trace 23.2M citation edges.Remote & Local · HTTP, stdioLive check: ✓ handshakemcp.scholarfeed.org
Scholar MCPFederated academic search, citation traversal, persistent PDF download, and temporary reading.Local · stdioPyPI: scholar-mcp
Scholar MCPFastMCP server for scholarly papers, patents, books and standards with docling PDF conversion.Local · stdio, HTTPPyPI: pvliesdonk-scholar-mcp
Scholar SidekickCatch AI-fabricated citations (real DOI + fake title). Retraction, open-access, 10,000+ CSL styles.Remote & Local · HTTP, stdioLive check: ✓ handshakescholar-sidekick.com
ScholarFetchMulti-engine scholarly research server for search, traversal, full text, and reading lists.Remote · HTTPLive check: ✓ handshakelaibniz-scholarfetch-web.hf.space
SchoolScopeCalifornia school data for AI agents - scores, profiles, comparisons, feeder paths, UC pipelines.Remote · HTTPLive check: ✓ handshakemcp.schoolscope.co
Science AI Journal MCP ServerAcademic peer-review, research-gap finding, journal recommender, and article writer tools.Local · stdionpm: science-ai-mcp-server