Scholar MCP

io.github.Liyux3Published by GitHub account Liyux3v0.10.0Updated Nov 7, 2026

Federated academic search, citation traversal, persistent PDF download, and temporary reading.

VerifiedSTDIODesktop onlyWeb Search & ScrapingFiles & StorageKnowledge & Memory

Overview

AI-generated overview

Gives an AI assistant a research library: federated scholarly search, citation traversal, paper reading, and a local library of saved PDFs and notes.

What you can do
  • Search scholarly sources in parallel, merging duplicates and reranking results, and inspect a paper's metadata, citations and references
  • Explore related work through semantic neighbours, co-cited papers and shared references, and look up author profiles and metrics
  • Read papers as page-aware Markdown with tables and figure images, and download PDFs into a local library
  • Build citation graphs with PageRank and bridge papers, and manage collections, notes, tags and full-text search (research profile)
  • Mirror the library to Obsidian, Zotero or Notion, with notes edited there flowing back
When to use it
Useful when you want an assistant to do literature reviews, find and compare papers, follow citation trails, or keep a persistent, searchable research library across sessions. It suits research and education use; commercial use requires a separate license.
Requirements
Runs locally over stdio as a PyPI package launched with uvx (Python 3.12), or via the installer, container or desktop bundle. No keys are required; optional keys such as S2_API_KEY, OPENALEX_API_KEY, DASHSCOPE_API_KEY, SCOPUS_API_KEY, CORE_API_KEY, EXA_API_KEY, ZOTERO_API_KEY and NOTION_API_KEY add sources, throughput or connectors. Network access is needed for search and downloads.
Before you install
Optional keys are stored in a local keys file and grant access to third-party services. Institutional access requires an EZproxy prefix and a browser cookies.txt, which are sensitive credentials. Google Scholar recovery launches a headless browser and stores sessions locally. The server writes a local library, PDFs and usage logs, and syncs data to Obsidian, Zotero or Notion when configured. Free only for noncommercial research and education.

Installation

In SourceWeft

  1. Open Scholar MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[Scholar MCP]

[Install in VS Code] [Add to Cursor] [Add to Kiro] [MCP Registry] [PyPI] [PolyForm Noncommercial 1.0.0 with additional terms]

Find the paper. Follow the evidence. Build the field.
Documentation · English · 简体中文

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. Free for research and education, with commercial licenses for companies.

[Watch the one-minute film]

📰 News

  • November 2026, 0.10.0. Searches no longer wait on a source whose connection hangs, OpenAlex's daily allowance lasts about four times as long, and Scholar is free for research and education under PolyForm Noncommercial, with commercial licenses for companies.
  • November 2026, 0.9.0. scholar-mcp install sets Scholar up in 32 agents, one key file serves all of them, a slow source no longer holds up the others, and scholar-mcp doctor --network checks every link.
  • October 2026, 0.8.5. Google Scholar sessions recover on their own, and arXiv falls back to its own search when its API is down.

🚀 Get started

  1. Install uv if you do not have it, then install Scholar:

    bash
    uv tool install --python 3.12 --find-links https://github.com/Liyux3/scholar-mcp/releases/latest/download/wheel-index.html "scholar-mcp[rerank]"

  2. 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.

  3. 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:

json
{  "mcpServers": {    "scholar": {      "command": "uvx",      "args": [        "--python", "3.12",        "--find-links", "https://github.com/Liyux3/scholar-mcp/releases/latest/download/wheel-index.html",        "--from", "scholar-mcp[rerank]", "scholar-mcp"      ]    }  }}

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-mcpclaude 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.

🧰 What your agent can do

Tool
Searchsearch_papersOne 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
Inspectpaper_infoFull metadata, citations and references of a paper in one call
Explorerecommend_papersSemantic neighbours, co-cited peers and papers sharing references
Peoplesearch_authorsAuthor profiles, affiliations and metrics
Readread_paperPage-aware Markdown, structured tables and a focused image of any figure, read temporarily
Keepdownload_paperThe PDF from open archives, repositories or your institution's library, filed in your library
Mapbuild_paper_graphA citation graph with PageRank and bridge papers (research profile)
Rememberpaper_libraryCollections, 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.

🧭 How it works

[Scholar MCP retrieval pipeline]

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 [Scholar MCP 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.

📊 Measured retrieval quality

[LitSearch quality comparison]

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
SystemHit@5Hit@10Hit@20MRR
Scholar0.620.680.700.442
Exa research paper0.520.580.640.435
BM25 title + abstract0.460.460.560.335

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.

📚 Your paper library

[Real paper-library graph]

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.

bash
scholar-mcp library export obsidian --collection memory --path ~/Vaultscholar-mcp library sync zotero --collection memory --apply

💻 Command line and Python

The tools work without an agent too. Output is YAML for reading or JSON with --json.

bash
scholar-mcp search "long-term memory benchmarks for LLM agents" --year 2024-2026scholar-mcp read arXiv:2504.19413 --pages 1-4scholar-mcp read arXiv:2504.19413 --visual "Figure 1" --image figure1.pngscholar-mcp doctor --network
python
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")

🔑 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.

VariableEffect
S2_API_KEYHigher Semantic Scholar limits, full-text snippets and recommendations
OPENALEX_API_KEY, OPENALEX_EMAILOpenAlex semantic search and a larger daily allowance; the email serves Crossref's polite pool and Unpaywall
DASHSCOPE_API_KEYCloud reranking with Qwen3 Rerank; without it a local model ranks
SCHOLAR_MCP_EXTENSIONS=researchAdds the citation graph and paper library tools
SCHOLAR_DATA_DIRLibrary, PDFs and state; default ~/.scholar-mcp
All settings
VariablePurpose
SCHOLAR_KB_DIR, SCHOLAR_DOWNLOAD_DIRSQLite library and persistent PDF directories
SCHOLAR_OBSIDIAN_VAULTObsidian projection root
S2_API_KEYS, OPENALEX_API_KEYSComma-separated key pools
NCBI_API_KEYHigher PubMed E-utilities throughput for a configured NCBI account
SCHOLAR_GOOGLE_PROXYA dedicated Google Scholar proxy, or direct to bypass inherited proxies for this source
SCHOLAR_ACCESS_COMMANDOptional host access backend, a JSON command array; see host access
SCOPUS_API_KEY, CORE_API_KEY, EXA_API_KEYOptional Scopus, CORE and Exa sources
OPENAIRE_CLIENT_ID, OPENAIRE_CLIENT_SECRETA free registered OpenAIRE service: 7,200 requests an hour instead of 60
ADS_API_TOKEN, SPRINGER_API_KEY, WOS_API_KEY, LENS_API_TOKENOpt-in NASA ADS, Springer Nature, Web of Science Starter and Lens sources, each joining once its key is set
DASHSCOPE_HTTP_BASE_URLAlibaba workspace API host or /api/v1 base; default is the Beijing shared endpoint
SCHOLAR_RERANK_MODELAlibaba model (default qwen3-rerank) or the model of a custom endpoint
SCHOLAR_RERANK_URL, SCHOLAR_RERANK_API_KEYFull custom rerank endpoint (Cohere-style query, documents, top_n request) and its credential
SCHOLAR_RERANK_TIMEOUT, SCHOLAR_RERANK_BATCH_SIZERemote rerank timeout (120 s) and per-request document capacity (500)
SCHOLAR_SOURCE_BUDGET_STime budget of one parallel search round; default 30 s
SCHOLAR_READ_CHAR_BUDGETCharacters of paper text per read_paper response, cut at a page boundary; default 100,000, 0 disables
SCHOLAR_USAGE_LOGLocal 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_RECOVERYGoogle Scholar route and browser recovery mode (off, headless, headed)
LIBRARY_PROXY_PREFIX, LIBRARY_PROXY_COOKIESInstitutional EZproxy prefix and a cookies.txt from your signed-in browser
ZOTERO_API_KEY, ZOTERO_LIBRARY_IDZotero connector
NOTION_API_KEY, NOTION_DATA_SOURCE_IDNotion connector
SCHOLAR_MCP_TRANSPORT=httpStreamable HTTP at /mcp instead of stdio (scholar-mcp serve --http)
SCHOLAR_IDLE_EXITHTTP 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.

bash
export LIBRARY_PROXY_PREFIX="https://proxy.library.example.edu/login?url="export LIBRARY_PROXY_COOKIES="$HOME/private/library-cookies.txt"

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.

🔧 Development

bash
git clone https://github.com/Liyux3/scholar-mcp.gitcd scholar-mcpuv sync --extra devuv 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.

📝 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 = {0.10.0},  url     = {https://github.com/Liyux3/scholar-mcp},  license = {PolyForm Noncommercial 1.0.0 with additional terms}}

📄 License

PolyForm Noncommercial 1.0.0 with additional terms, source-available. Free for personal research, universities, research institutes, government and nonprofits; companies using Scholar in their work, products or services need a commercial license, write to [email protected]. Copying or porting its code into a competing project, and training models on its code or documentation, are not licensed; AGENTS.md tells coding agents the same and what to offer instead. If Scholar's ideas or results inform your work, please cite it. Releases 0.9.0 and earlier remain under Apache-2.0. See also NOTICE.

Bundled CPU reader weights are provided unchanged by prithivida/FlashRank under CC-BY-SA-4.0, with their own attribution notice.

Source: README.md at commit 93a1867

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

4
  1. v0.10.0LatestNov 7, 2026
  2. v0.9.0Nov 3, 2026
  3. v0.8.5Oct 7, 2026
  4. v0.8.4Sep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.