This MCP server provides federated academic search, citation traversal, persistent PDF download, and temporary reading. It is organized as a research-focused MCP server with topics including academic-search, paper-search, citation-graph, and literature-review.
๐ ๏ธ Key Features
Federated academic search
Citation traversal
Persistent PDF download
Temporary reading
๐ Use Cases
Searching across academic sources
Following citations through related papers (citation traversal)
Downloading PDFs for ongoing access (persistent PDF download)
Reviewing content with time-bounded reading (temporary reading)
โก Developer Benefits
Supports model-driven research workflows via MCP
Clear tool scope around search, citation graph traversal, and PDF handling
โ ๏ธ Limitations
Readme excerpt provided does not include additional constraints (e.g., rate limits, supported formats, or system requirements).
Scholar MCP gives your AI agent a research library. It searches scholarly sources in parallel, with optional keys for additional indexes, follows citations and related work, reads the original paper down to its figures and tables, and keeps what matters in a local library with your notes. It works in Claude, Codex, Cursor, VS Code, Gemini CLI, OpenCode and any other MCP client, and from the command line or Python.
๐ฐ News
November 2026, 0.9.0 to 0.11.0. scholar-mcp install sets Scholar up in 32 agents, a hung source no longer holds up a search, windows narrow to the month or day, results carry full abstracts, and author search finds the right person behind a well-known name.
July 2026, 0.8.5. Google Scholar sessions recover on their own, arXiv falls back to its own search when its API is down, and scholar-mcp sources --check tests every provider live.
April 2026, 0.8.2 to 0.8.4. Semantic Scholar requests follow the provider's pacing, the MCP Registry entry resolves as io.github.Liyux3/scholar-mcp, and every tool says when to use it.
Earlier news
February 2026, 0.8.0 and 0.8.1. Six core tools connect to a persistent research library, and plugins and a portable launcher bring Scholar to more agent clients.
July 2025, 0.7.1 and 0.7.2. A source that throttles is reported instead of looking empty, one slow source can no longer stall a search, and citation graphs and related papers work again for arXiv papers.
May 2025, 0.6.0 and 0.7.0. Papers keep their notes in a library of collections, a relevance model ranks every candidate together, strong matches bring in their citations, and Europe PMC, INSPIRE-HEP and DBLP join the sources.
December 2024, 0.1.0 to 0.2.1. The first release searches Semantic Scholar from Claude Code with one command; CORE and PubMed join within days.
Connect it to your agents. Scholar finds the clients on your machine and registers itself, with a backup of every file it touches:
bash
scholar-mcp install --all
In a client the installer does not know, ask your agent to install Scholar by following llms-install.md. Name clients to choose (scholar-mcp install claude-code codex), add --dry-run to preview the change, or --profile research for the citation graph and paper library tools. scholar-mcp update upgrades the command every connected client runs, and uvx scholar-mcp@latest install CLIENT refreshes a client pinned to a uvx version.
Restart the client and ask a research question, for example find recent work on evaluating long-term memory in LLM agents, read the most cited one and compare its benchmarks.
Other ways to install
Any stdio MCP client can launch Scholar directly through uvx, with nothing installed in advance:
For Claude Code the same command is claude mcp add scholar -- uvx --python 3.12 --find-links <index> --from 'scholar-mcp[rerank]' scholar-mcp.
The repository is also a plugin marketplace for Codex and Claude Code, bundling the research tools and the Deep Research skill:
bash
codex plugin marketplace add Liyux3/scholar-mcp && codex plugin add scholar-mcp@scholar-mcp
claude plugin marketplace add Liyux3/scholar-mcp && claude plugin install scholar-mcp@scholar-mcp
Releases also ship macOS desktop bundles (MCPB) with Python included, a multi-architecture container at ghcr.io/liyux3/scholar-mcp, and the MCP Registry entry. See the distribution matrix and llms-install.md for agents installing it themselves.
๐งฐ What your agent can do
Tool
Search
search_papers
One question fans out to every source; duplicates merge into one record, the pool is reranked, and citations of the best matches are followed before the final ranking
Inspect
paper_info
Full metadata, citations and references of a paper in one call
Explore
recommend_papers
Semantic neighbours, co-cited peers and papers sharing references
People
search_authors
Author profiles, affiliations and metrics
Read
read_paper
Page-aware Markdown, structured tables and a focused image of any figure, read temporarily
Keep
download_paper
The PDF from open archives, repositories or your institution's library, filed in your library
Map
build_paper_graph
A citation graph with PageRank and bridge papers (research profile)
Remember
paper_library
Collections, notes, tags and full-text search, mirrored to Obsidian, Zotero or Notion (research profile)
Every identifier Scholar returns, a paper URL, or an exact title can be passed back to any tool. Responses carry readable YAML for the model and structured data for the client; scholar://status reports the sources and reranker in use.
๐งญ How it works
Your question goes to every source at once, in the form each one searches best, and no source holds up the others. Records from OpenAlex, Semantic Scholar, arXiv, Crossref, OpenReview, PubMed, Europe PMC, DBLP, zbMATH, CORE, OpenAIRE, Google Scholar and others merge on shared DOIs, arXiv ids and titles, so each paper appears once with complementary metadata. A ranking model, in the cloud or on your machine, orders the pool, the strongest papers bring in their citations and references, and everything is ranked together. The architecture page shows what each stage does for you and the backend film follows one question through it in two and a half minutes.
Runtime architecture
Agents call typed MCP tools over stdio or Streamable HTTP. Full text comes from open copies first and, for licensed papers, through your library's proxy. A persistent SQLite library with FTS5 search holds papers, notes and PDF attachments under ~/.scholar-mcp/, with Markdown projections for Obsidian and connectors for Zotero and Notion.
๐ Measured retrieval quality
On the same 50 LitSearch queries, Scholar placed a correct paper in its top five for 62% of queries, against 52% for Exa research-paper search and 46% for BM25.
Results and protocol
System
Hit@5
Hit@10
Hit@20
MRR
Scholar
0.62
0.68
0.70
0.442
Exa research paper
0.52
0.58
0.64
0.435
BM25 title + abstract
0.46
0.46
0.56
0.335
Hit@k is the share of queries with at least one ground-truth paper in the top k; MRR averages the reciprocal rank of the first match. Scholar recovered nine top-five hits that Exa missed, and Exa four that Scholar missed. The comparison uses the first 50 LitSearch inline-ACL queries, the same title matcher and a top-20 cutoff; Scholar ran its standard pipeline with Qwen reranking, Exa used category research paper, and BM25 follows the official LitSearch title+abstract implementation over the 64K-paper corpus. The frozen summary is in docs/benchmarks/litsearch-inline-acl-50.json, with raw BM25 results and their hash manifest.
๐ Your paper library
Saved papers, PDFs and notes live in one local SQLite library and stay searchable across sessions. Obsidian receives a live Markdown projection, Zotero a synchronized collection and Notion a reading list. Notes you edit in Obsidian or Notion flow back, so your agent builds on your changes.
The tools work without an agent too. Output is YAML for reading or JSON with --json. --year takes a year, a range or an exact window, such as 2023, 2020-2024, 2026-10, 2026-10:2026-11 or 2026-10-01..2026-11-09, and a month covers all its days.
from scholar_mcp import api
hits = api.search("long-term memory benchmarks for LLM agents", year="2024-2026")
paper = api.info(hits["results"][0]["id"], include="detail,citations")
๐ Configuration
Scholar works without any keys. Optional keys add coverage and throughput. scholar-mcp keys set NAME saves one in ~/.scholar-mcp/keys.env, which every client reads; a client's env block or your shell also works and takes precedence.
Variable
Effect
S2_API_KEY
Higher Semantic Scholar limits, full-text snippets and recommendations
OPENALEX_API_KEY, OPENALEX_EMAIL
OpenAlex semantic search and a larger daily allowance; the email serves Crossref's polite pool and Unpaywall
DASHSCOPE_API_KEY
Cloud reranking with Qwen3 Rerank; without it a local model ranks
SCHOLAR_MCP_EXTENSIONS=research
Adds the citation graph and paper library tools
SCHOLAR_DATA_DIR
Library, PDFs and state; default ~/.scholar-mcp
All settings
Variable
Purpose
SCHOLAR_KB_DIR, SCHOLAR_DOWNLOAD_DIR
SQLite library and persistent PDF directories
SCHOLAR_OBSIDIAN_VAULT
Obsidian projection root
S2_API_KEYS, OPENALEX_API_KEYS
Comma-separated key pools
NCBI_API_KEY
Higher PubMed E-utilities throughput for a configured NCBI account
SCHOLAR_GOOGLE_PROXY
A dedicated Google Scholar proxy, or direct to bypass inherited proxies for this source
SCHOLAR_ACCESS_COMMAND
Optional host access backend, a JSON command array; see host access
SCOPUS_API_KEY, CORE_API_KEY, EXA_API_KEY
Optional Scopus, CORE and Exa sources
OPENAIRE_CLIENT_ID, OPENAIRE_CLIENT_SECRET
A free registered OpenAIRE service: 7,200 requests an hour instead of 60
Opt-in NASA ADS, Springer Nature, Web of Science Starter and Lens sources, each joining once its key is set
DASHSCOPE_HTTP_BASE_URL
Alibaba workspace API host or /api/v1 base; default is the Beijing shared endpoint
SCHOLAR_RERANK_MODEL
Alibaba model (default qwen3-rerank) or the model of a custom endpoint
SCHOLAR_RERANK_URL, SCHOLAR_RERANK_API_KEY
Full custom rerank endpoint (Cohere-style query, documents, top_n request) and its credential
SCHOLAR_RERANK_TIMEOUT, SCHOLAR_RERANK_BATCH_SIZE
Remote rerank timeout (120 s) and per-request document capacity (500)
SCHOLAR_SOURCE_BUDGET_S
Time budget of one parallel search round; default 30 s
SCHOLAR_READ_CHAR_BUDGET
Characters of paper text per read_paper response, cut at a page boundary; default 100,000, 0 disables
SCHOLAR_USAGE_LOG
Local call record in <data>/usage/ (about 4 MB at most) that doctor summarizes: on (default, no query text), full (with arguments) or off
SCHOLAR_GOOGLE_PROXY, SCHOLAR_GOOGLE_RECOVERY
Google Scholar route and browser recovery mode (off, headless, headed)
LIBRARY_PROXY_PREFIX, LIBRARY_PROXY_COOKIES
Institutional EZproxy prefix and a cookies.txt from your signed-in browser
ZOTERO_API_KEY, ZOTERO_LIBRARY_ID
Zotero connector
NOTION_API_KEY, NOTION_DATA_SOURCE_ID
Notion connector
SCHOLAR_MCP_TRANSPORT=http
Streamable HTTP at /mcp instead of stdio (scholar-mcp serve --http)
SCHOLAR_IDLE_EXIT
HTTP idle exit in minutes, default 20; 0 keeps the process running. A supervisor such as launchd KeepAlive restarts it to release loaded model memory. Active tool workers and streamed replies finish before the idle window starts.
Scores from a custom reranker must be finite, in [0, 1] and comparable across batches; Scholar falls back to the local model when the endpoint fails and pauses retries for five minutes after a connection failure. Errors returned to the model redact URLs and credentials.
Paywalled papers and your institution's library
download_paper and read_paper look for free copies in parallel and prefer the publisher's version when one arrives. To use a paper your institution licenses, set its EZproxy prefix and a Netscape cookies.txt exported from your signed-in browser in the server's environment.
Scholar reads only cookies scoped to that proxy. When the session expires, sign in through your browser and export a fresh file. See Institutional access for client configuration and network routing.
Google Scholar
With Chrome, Edge or Chromium and ffmpeg installed, scholar-mcp[google,rerank] adds automatic verification recovery: a short-lived headless browser with a fresh profile establishes a session, then ordinary HTTP handles searches and pagination. Sessions are stored privately under <data>/sessions/. Set SCHOLAR_GOOGLE_RECOVERY=off to disable it.
๐ง Development
bash
git clone https://github.com/Liyux3/scholar-mcp.git
cd scholar-mcp
uv sync --extra dev
uv run pytest # unit tests; live API tests run with -m integration
A new source is one module in scholar_mcp/sources/ plus one registry entry, and needs no new tool. scholar-mcp doctor --network probes every source, the ranking model and the PDF chain, and runs daily in CI. See CONTRIBUTING.md for changes, and report security issues through SECURITY.md.
๐ Citation
If Scholar MCP supports your research, please cite it.
bibtex
@software{li_scholar_mcp_2026,
author = {Li, Yuxian},
title = {Scholar MCP},
year = {2026},
version = {0.11.0},
url = {https://github.com/Liyux3/scholar-mcp},
license = {PolyForm Noncommercial 1.0.0 with additional terms}
}
๐ License
PolyForm Noncommercial 1.0.0 with additional terms
The license and its additional terms make Scholar free for research and education; commercial use needs a license. Bundled CPU reader weights are provided unchanged by prithivida/FlashRank under CC-BY-SA-4.0, with their own attribution notice.
Install
Configuration
Environment variables
SCHOLAR_DATA_DIR
SCHOLAR_MCP_EXTENSIONS
S2_API_KEYsecret
OPENALEX_API_KEYsecret
CORE_API_KEYsecret
SCOPUS_API_KEYsecret
DASHSCOPE_API_KEYsecret
DASHSCOPE_HTTP_BASE_URL
Alibaba workspace API host or /api/v1 base URL.
SCHOLAR_RERANK_MODEL
Alibaba or custom reranker model name.
SCHOLAR_RERANK_URL
Full custom rerank endpoint; overrides Alibaba routing.