Scholar MCP

Scholar MCP

[CI] [Quality Gate Status] [Coverage] [Reliability Rating] [Security Rating] [PyPI] [Python] [License] [Docker] [Docs] [llms.txt] [Template]

Scholarly papers, patents, books, standards and PDF conversion

Documentation | Config wizard | PyPI | Docker

29 tools, organised by scholarly source type.

Source domains

• Papers: full-text search with year/venue/field/citation filters; single-paper lookup by DOI, S2 ID, arXiv ID, ACM ID, or PubMed ID; author profile and name search; forward citations, backward references, BFS graph traversal, shortest-path bridge discovery; recommendations from positive/negative examples; BibTeX/CSL-JSON/RIS citation generation with OpenAlex venue enrichment.
• Patents: search across 100+ patent offices via EPO OPS with CPC/applicant/inventor/jurisdiction filters; bibliographic, claims, description, family, legal, and citations sections; NPL-to-paper resolution via Semantic Scholar and paper-to-patent citation discovery. EPO credentials are optional; other domains work without them.
• Books: Open Library search by title/author/keywords, no API key required; lookup by ISBN-10/13 or by Open Library work/edition ID; subject-based recommendations sorted by popularity; Google Books excerpts and preview links; WorldCat permalinks for library discovery; cover image caching. Papers with an ISBN in externalIds are automatically enriched with publisher, edition, cover URL, and subject data from Open Library.
• Standards: identifier resolution, search, and metadata retrieval for NIST, IETF, W3C, and ETSI standards, with optional full-text fetch and Markdown conversion via docling. Tier 2 ISO, IEC, IEEE, Common Criteria (CC), and CEN/CENELEC metadata (including ISO/IEC/IEEE joint standards and the CC ↔ ISO/IEC 15408 cross-link) is synced locally via sync-standards. ISO, IEC, IEEE have a live-fetch fallback for unsynced identifiers; CC and CEN have no live API and require a sync first. Citations matching standards patterns (RFC, ISO, NIST SP, IEEE, EN, CC) are automatically enriched with structured standard_metadata including identifier, title, body, status, and full-text URL when available (see docs/use/standards.md).

Cross-cutting

• Enrichment pipeline: phased enrichment from multiple sources: OpenAlex (OA status, affiliations, funders, concepts), CrossRef (publisher, page ranges, container titles), Google Books (preview links, excerpts), and Open Library (book metadata). Runs automatically on paper and book results.
• PDF conversion: download open-access PDFs and convert to Markdown via docling-serve, with optional VLM enrichment for formulas and figures; automatic fallback to ArXiv, PubMed Central, and Unpaywall when Semantic Scholar has no OA link; direct URL download for PDFs found elsewhere; converted text is paged so large documents fit in MCP responses.
• Intelligent caching: SQLite-backed cache with per-table TTLs (30 days for papers/authors, 7 days for citations/references) and identifier aliasing.

Coverage by domain

Per-domain depth is uneven. Papers currently have the richest tool surface (citation graph, recommendations, cross-referencing to all three other domains); standards are the leanest. That reflects public data availability, not a value hierarchy: writing a paper typically needs all four source types for citations and prior art. Parity work is tracked in GitHub issues and milestones; the roadmap shows intent, not a completeness commitment.

Does it fit?

What the server can reach, what it changes and who gets in is set out in the security model; the block below says who it serves and where it stops.

With this server mounted in an MCP client (Claude, etc.), you can:

• Survey a field: "Find the 20 most-cited papers on graph neural networks from 2020 to 2024 and draft a literature review outline." Composes search_papers + get_citations + enrich_paper.
• Trace a citation path: "What's the shortest citation path from 'Attention is All You Need' to 'RLHF for dialogue agents'?" Uses find_bridge_papers + get_citation_graph.
• Cross-reference prior art: "For this patent family, list academic papers it cites and any books or standards that show up in the description." Composes get_patent + batch_resolve + standards/book enrichment.
• Generate a bibliography: "Emit BibTeX for these 30 DOIs with OpenAlex venue data." Uses generate_citations.
• Look up a standard: "What's the latest status of RFC 9000, and fetch the Markdown full text." Uses resolve_standard_identifier + get_standard.

It reaches public scholarly metadata and open-access full text; it doesn't get past paywalls, and paywalled standards (ISO, IEC, IEEE) come back as metadata only. Patent tools need your own EPO OPS credentials.

Quick start

Pick the client you use. Each line installs the released version; the Get started tutorials carry on from there.

Claude Desktop. Download the .mcpb bundle from the releases page and open it with Claude Desktop (or Settings › Extensions › Advanced settings › Install Extension…). Claude Desktop asks for the required settings itself. Tutorial.

Claude Code. Two commands inside Claude Code; the second asks for a scope. Tutorial.

/plugin marketplace add pvliesdonk/claude-plugins/plugin install scholar-mcp@pvliesdonk

A client that runs a command (stdio). To register it in Claude Code, see the Claude Code tutorial.

uv tool install "pvliesdonk-scholar-mcp"scholar-mcp serve

A server for remote clients (streamable HTTP). A remote server connects the clients.

docker run --rm -p 8000:8000 --env-file .env ghcr.io/pvliesdonk/scholar-mcp:latest

A compose.yml ships at the repository root and runs as-is: copy .env.example to .env, then docker compose up -d. Deploy covers authentication, OIDC, a reverse proxy and system packages (.deb/.rpm on the releases page). The server answers /health and /health/ready outside the MCP mount, and its get_server_info tool reports the running version.

• [all]: every production feature in one extra; the Linux packages and the Claude Desktop bundle install it.
• [debug]: adds the remote debugger (debugpy); see Remote debugging.

The base package already carries FastMCP through fastmcp-pvl-core, so pip install pvliesdonk-scholar-mcp is enough to run scholar-mcp serve. The older [mcp] extra is kept so existing install commands keep working; it adds nothing beyond the base package.

Configuration

Everything is configured through environment variables with the SCHOLAR_MCP_ prefix. The ones most installs set:

Every variable the server reads, the shared ones included, is in the configuration reference; .env.example lists the same surface in copy-paste form, and the config wizard writes one for your deployment.

Documentation

• Security model: what the server can reach, what it changes and who gets in.
• Get started: a first success with your client.
• Deploy: Docker, authentication, OIDC, reverse proxy.
• Use: the features, for real tasks.
• Reference: configuration, tools, resources, prompts, command line.
• Upgrade: release channels, and what an upgrade changes for your clients and your data.
• Contribute: local development, secrets, where a fix belongs; CONTRIBUTING.md and SECURITY.md at the root.

Design decisions

• Domain logic apart from the MCP layer. The upstream clients (Semantic Scholar, OpenAlex, EPO, Open Library, standards bodies), the enrichment pipeline and the cache don't import FastMCP; the tool modules are thin wrappers over them.
• Async clients, blocking libraries off the event loop. The HTTP clients and the SQLite cache are async. The blocking pieces (the python-epo-ops-client library, file I/O around PDF download and conversion, the Relaton sync) run through asyncio.to_thread().
• SQLite cache with per-table TTLs and identifier aliases. Papers / authors last 30 days, citations / references 7 days. DOI ↔ S2 ID ↔ arXiv ID aliasing survives across cache clears so repeated enrichment hits the same row.
• Read-only by default. Write-tagged tools (PDF download/convert, patent PDF) are hidden unless SCHOLAR_MCP_READ_ONLY=false. Safer default for first-run.
• Slow work becomes a background job. Every tool whose work can run long uses the fastmcp-pvl-core jobs layer. A call that beats SCHOLAR_MCP_JOBS_SOFT_DEADLINE_S returns its result directly; a slower one returns a handle to poll with get_job_result. S2-backed tools also return a reasoned handle as soon as Semantic Scholar throttles them. The work continues from where it paused, and a cache hit still answers directly.
• EPO throttling is waited out, not queued. The traffic light is consulted before every request and cached for a minute, so a retry sooner than that would re-read the cache rather than ask again. Each backoff outlasts the cache; an exhausted daily quota is reported immediately instead, since it will not clear today.
• Tier 2 standards sync out-of-band. ISO/IEC/IEEE/CC/CEN catalogues come from community Relaton dumps via scholar-mcp sync-standards, not live at runtime, which avoids paywalled-HTML scraping and keeps tool calls fast.

Links

• Documentation and its llms.txt
• FastMCP and fastmcp-pvl-core, which this server is built on
• fastmcp-server-template, which generated this repository