Scholar MCP

Go deeper.

Find the paper. Follow the evidence. Build the field.

Scholar MCP turns a research question into a connected body of evidence. It recovers papers from vague descriptions, reaches the work one hop beyond search, opens the primary text, maps the lineage, and carries the selected field into a library that grows with every session.

Natural-language discovery · Related-work discovery · Primary evidence · Field maps · Zotero · Obsidian · Notion connectors

Quick demo

One continuous agent flow: search_papers → build_paper_graph → paper_info + read_paper → paper_library → library connectors.

How it works

Agents call typed MCP tools over stdio or Streamable HTTP. Scholar returns concise text and structured data, while a persistent SQLite library drives FTS5 search, PDF attachments, JSONL snapshots, and Obsidian, Zotero, and Notion connectors.

Quick start

Claude Code:

claude mcp add scholar -- uvx scholar-mcp

Claude Desktop or any stdio MCP client:

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

The direct server exposes the compact core profile. Python 3.10+ and uv are required. Optional source keys unlock deeper coverage and higher throughput.

The repository also ships a research plugin with citation graphs, a local paper library, and the Deep Research skill:

# Codex
codex plugin marketplace add Liyux3/scholar-mcp
codex plugin add scholar-mcp@scholar-mcp

# Claude Code
claude plugin marketplace add Liyux3/scholar-mcp
claude plugin install scholar-mcp@scholar-mcp

The same plugin directory follows the Agent Plugins standard for Cursor, Pi, and compatible harnesses. OpenCode can launch uvx scholar-mcp as a local MCP; Pi can use pi-mcp-adapter.

Release artifacts also include the PyPI package, multi-architecture GHCR image, and macOS MCPB bundles. See the complete distribution matrix.

Tools

scholar://status reports source availability and the actual reranker used without occupying the tool surface. Tool responses retain concise YAML text and also expose structured MCP data.

The bundled Deep Research skill turns search, paper inspection, graph traversal, and selected library writes into a living field map.

Retrieval

Keyword APIs receive measured source-specific query budgets. Semantic endpoints keep the original question. Every source contributes independently to one canonical evidence pool.

Results are canonicalized across DOI, arXiv, Semantic Scholar, OpenAlex, PubMed, and OpenReview identities. Duplicate records contribute complementary metadata and independent source evidence instead of appearing several times.

DashScope qwen3-rerank is the primary reranker when configured; FlashRank is the local fallback. The normal response shows only source coverage, the actual reranker, and actionable degradation. debug=true adds per-source yield, latency, provenance, and internal ranking diagnostics.

Measured retrieval quality

Scholar leads the Exa research-paper baseline by 10 points at R@5 and 6 points at R@20 on matched LitSearch.

Scholar recovered nine R@5 hits that Exa missed; Exa recovered four that Scholar missed.

Benchmark protocol

The comparison uses the same first 50 LitSearch inline-ACL queries, ground-truth titles, title matcher, and top-20 cutoff. Exa ran with category research paper. Scholar used its standard retrieval pipeline with Qwen reranking. BM25 follows the official LitSearch title+abstract implementation: lowercase tokenization, English stopword removal, Porter stemming, and BM25Okapi over the 64K-paper corpus. The Scholar/Exa run was collected on 12 May 2026; BM25 was reproduced on 25 August 2026. The frozen summary is in docs/benchmarks/litsearch-inline-acl-50.json, with raw BM25 results and their hash manifest.

Citation graph and paper library

Rendered from a live local collection, the graph reveals foundations, bridges, and the papers that move a field forward. Stable identities and parallel citation traversal keep the map connected as it grows.

The paper library uses one persistent SQLite authority with WAL transactions and FTS5 search. Existing JSONL collections migrate automatically and remain available as compatibility snapshots. Stable identifiers, notes, tags, PDF paths, connector IDs, and sync revisions stay attached to the same canonical record.

Default data layout:

~/.scholar-mcp/
├── papers/    persistent PDFs
├── kb/
│   ├── library.sqlite3    authority + FTS5 + sync state
│   └── *.jsonl            compatibility snapshots
└── vault/                 Markdown projections and wikilinks

Library connectors

# No login: write directly into an Obsidian vault
scholar-mcp library export obsidian --collection rag --path /path/to/vault

# Dry-run by default; add --apply for external writes
scholar-mcp library sync zotero --collection rag
scholar-mcp library publish notion --collection rag

Obsidian is a live Markdown projection. Zotero manages bibliographic items, collections, tags, and notes. Notion receives a one-way reading-list view. External connectors keep their IDs, versions, and content hashes in SQLite, so unchanged papers do not publish twice.

Paper access

read_paper uses a temporary PDF and reads pages 1-10 by default, which usually reaches the conclusion of an AI conference paper. It returns page-aware Markdown, structured tables when their geometry is reliable, and caption selectors for figures and visual table fallbacks. Pass visual="Figure 3" or another returned selector to receive one focused page crop alongside its text. Pass pages="11-20" to continue into references or appendices. The PDF is removed after extraction. download_paper streams into a staging file, atomically publishes a validated PDF, reuses a valid local copy, and indexes its metadata in the selected collection.

The shared resolution chain covers:

1. Native open-access records and canonical archives such as arXiv and Europe PMC
2. Registered repository resolvers: CORE, OpenAIRE, HAL, Zenodo, and DOAJ
3. bioRxiv, medRxiv, SSRN, ChemRxiv, and other preprint servers
4. Unpaywall and an optional institutional proxy
5. an explicit local fallback when enabled

scholar-mcp sources prints the live registry-derived capability matrix. Zenodo participates in PDF resolution but stays out of default discovery because its broad publication records add more candidate noise than retrieval value.

Configuration

All credentials are optional and remain in the MCP process environment.

Errors returned to the model redact request URLs and credentials.

Development

git clone https://github.com/Liyux3/scholar-mcp.git
cd scholar-mcp
uv sync --extra dev
uv run pytest

Unit tests are the default. Live API tests are marked integration and run separately with uv run pytest -m integration; pytest reports them as deselected during the deterministic unit run because the marker filter intentionally leaves network-dependent cases out of that invocation.

Connector and feature contributions follow CONTRIBUTING.md. Report security issues through the private process in SECURITY.md; citation metadata is available in CITATION.cff.

Local and Docker clients use stdio by default. Set SCHOLAR_MCP_TRANSPORT=http for Streamable HTTP; the default endpoint is /mcp.

License

Apache License 2.0