Scholar RAG MCP

scholar-rag-mcp is a publishable academic-paper knowledge-base MCP tool. Point it at a folder of PDFs and it ingests each paper through a real parsing pipeline (MinerU), normalizes metadata, annotates section structure, chunks and embeds the text, and stores everything in Qdrant - after which an agent (or you) can semantically search chunks, run PubMed-style document queries, read full text section by section…. Its 11 documented tools cover document, documents.

People who work with document and documents and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-04 · ★ 4 · #80 OF 208 MAINTAINED DOCUMENTATION · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install Scholar RAG MCP

before you install - you'll need

Set SCHOLAR_RAG_CHAT_BASE_URL, SCHOLAR_RAG_CHAT_MODEL, SCHOLAR_RAG_EMBED_BASE_URL, SCHOLAR_RAG_EMBED_MODEL, SCHOLAR_RAG_RERANK_BASE_URL, SCHOLAR_RAG_RERANK_MODEL before connecting.

Claude Code

claude mcp add notwhiteblank-scholar-rag-mcp -- uvx scholar-rag-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "notwhiteblank-scholar-rag-mcp": {
      "command": "uvx",
      "args": [
        "scholar-rag-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repo age created 2026-08-27 - young repo, little track record yet

license MIT - declared in the repository

pypi package scholar-rag-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.notwhiteblank is GitHub-verified and matches the repo owner

03 · What Scholar RAG MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can list knowledge bases with document/chunk counts and status, and query status/progress/result/elapsed time of a background job.

Capability map

Tools grouped from the project's README - what Scholar RAG MCP lets an agent do.

Document

4 tools - e.g. Asynchronously ingest a single PDF into an existing kb (returns job_id).; Synchronously delete one document (Qdrant points + catalog + files).; Document overview: metadata, abstract, section outline…

add_document · remove_document · get_document · get_document_text

read & search

3 tools - e.g. List knowledge bases with document/chunk counts and status.; Semantic chunk search with metadata filters and embed+rerank scores.; Query status/progress/result/elapsed time of a background job.

list_kbs · search_chunks · get_job

Documents

2 tools - e.g. Paginated browse of documents in a kb.; PubMed-style document-level search (FTS + title/authors/journal/year).

list_documents · search_documents

create & write

1 tool - e.g. Asynchronously ingest every PDF in a folder into a new kb (returns job_id).

create_kb

delete

1 tool - e.g. Two-phase kb deletion (see below).

delete_kb

04 · Who maintains Scholar RAG MCP

Scholar RAG MCP is maintained by notwhiteblank. It's the only MCP server we track from this author; the repo dates to Aug 2026.

05 · Facts

repository: github.com/notwhiteblank/scholar-rag-mcp
category: documentation - ranked #80 of 208 actively-maintained documentation servers as of 2026-09-18.
registry: io.github.notwhiteblank/scholar-rag-mcp (active, first published 2026-08-27 · 5 versions)
packages: pypi:scholar-rag-mcp

06 · Scholar RAG MCP FAQ

Is Scholar RAG MCP still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-04. We re-verify nightly.

What can Scholar RAG MCP do?

With this server connected, an agent can list knowledge bases with document/chunk counts and status, and query status/progress/result/elapsed time of a background job.

How do I install Scholar RAG MCP?

Run `uvx scholar-rag-mcp`. The README documents 6 environment variables (SCHOLAR_RAG_CHAT_BASE_URL, SCHOLAR_RAG_CHAT_MODEL, SCHOLAR_RAG_EMBED_BASE_URL…) to set first. Set SCHOLAR_RAG_CHAT_BASE_URL, SCHOLAR_RAG_CHAT_MODEL, SCHOLAR_RAG_EMBED_BASE_URL, SCHOLAR_RAG_EMBED_MODEL, SCHOLAR_RAG_RERANK_BASE_URL, SCHOLAR_RAG_RERANK_MODEL before connecting. You can also paste the ready-made client config above.

Does Scholar RAG MCP run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Scholar RAG MCP

Alternatives to Scholar RAG MCP

Maintained documentation servers if Scholar RAG MCP isn't the fit.

Pairs well with

Servers that cover what Scholar RAG MCP doesn't - only shown when the pairing reason fits the companion.

More documentation MCP servers · THOR · Markdown · Open & Async · MinerU Open MCP · Orderly MCP

More Python MCP servers · Yandex Analytics · MANNA · Tweetkit X · Snowflake MCP Server · AGENTS.md Generator · see all