version unknown

paper-search

openags@openags⭐ 3.1k stars· last commit 1mo ago· 11 open issues

Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc). Use when the user asks to find papers, search for research, look up academic literature, download a paper PDF, or extract text from a paper.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

7.1/10
Verified
Oct 12, 2026

// RATINGS

⭐GitHub Stars
⭐⭐⭐⭐⭐ 3.1k on GitHubGitHub ↗

Very popular

🟢ProSkills ScoreAI Verified
7.1/10
📍

Not yet listed on ClawHub or SkillsMP

// README

Paper Search MCP

A Model Context Protocol (MCP) server for searching and downloading academic papers from multiple sources. The project follows a free-first strategy: prioritize open and public data sources, support optional API keys when they improve stability or coverage, and keep source-specific connectors extensible for advanced users.

PyPI License Python smithery badge


Table of Contents


Overview

paper-search-mcp is a Python-based tool for searching and downloading academic papers from various platforms. It provides tools for searching papers, downloading PDFs, and extracting text, making it ideal for researchers and AI-driven workflows. It can be used as an MCP server (for Claude Desktop and other MCP clients) or as a Claude Code skill with a CLI interface.

Project Principles

  • Free-First: Public and open sources are the default roadmap. Paid or restricted sources are not the core direction of this project.
  • Optional API Keys: API keys are supported only when they improve stability, rate limits, or metadata quality. The MCP should still be usable without them whenever possible.
  • LLM-Friendly Retrieval: Search results should be standardized, deduplicated, and as complete as possible for downstream LLM workflows.
  • Source Transparency: Different sources have different strengths. The MCP should make those tradeoffs explicit instead of pretending every source supports full-text retrieval.

MCP Authorization Compatibility

The bundled MCP server supports stdio (the default), sse, and streamable-http. Network transports bind to 127.0.0.1 by default. Optional OAuth protected-resource mode adds standard discovery, JWT bearer-token validation and required scopes to both HTTP transports, using an external authorization server.

Enable it with --auth oauth or PAPER_SEARCH_MCP_AUTH=oauth and the explicit issuer/JWKS/resource/audience/scope configuration in OAuth protected-resource setup. Invalid or incomplete HTTP auth settings fail startup. stdio remains independent of HTTP authentication. Local HTTP without OAuth configuration remains open; do not publish that listener directly. A protected remote deployment still needs TLS, rate limits and filesystem isolation. This feature does not host login/accounts or replace the external issuer's OAuth flow; live identity-provider interoperability must be validated for your deployment.


Features

  • Two-Layer Architecture:
    • Layer 1 (Unified Tooling): High-level search_papers for multi-source concurrent search & deduplication, and download_with_fallback relying on publisher open access links with sequential fallbacks.
    • Layer 2 (Platform Connectors): Modular connectors for specific academic platforms (arXiv, PubMed, bioRxiv, Semantic Scholar, etc.) equipped with intelligent DOI extraction via regex text analysis or API fields.
  • Multi-Source Support: Search and download papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, IACR ePrint Archive, Semantic Scholar, Crossref, OpenAlex, PubMed Central (PMC), CORE, Europe PMC, dblp, OpenAIRE, CiteSeerX, DOAJ, BASE, Zenodo, HAL, SSRN, OpenReview, Unpaywall (DOI lookup), and optional Sci-Hub workflows.
  • Opt-in Fast Search: CLI search keeps broad coverage by default. Use -s fast (OpenAlex, Crossref, arXiv, PubMed, Europe PMC) or -s fastest (OpenAlex and Crossref) when lower latency matters more than coverage.
  • Standardized Output: Papers are returned in a consistent dictionary format via the Paper class.
  • Free-First Design: Open and public sources are prioritized before any optional commercial or restricted integrations.
  • Optional API-Key Enhancement: Sources like Semantic Scholar can work better with a user-provided API key, but are not intended to force paid usage.
  • Discovery + Retrieval Workflow: Google Scholar and Crossref can be used for discovery and DOI backfilling, while open repositories and publisher links are used for lawful full-text resolution where available.
  • OA-First Fallback Chain: download_with_fallback now follows source-native download → OpenAIRE/CORE/Europe PMC/PMC discovery → Unpaywall DOI resolution → optional Sci-Hub.
  • Bounded reference lookups: OpenAlex references and citing papers from a DOI or OpenAlex ID, with explicit budgets and truncation metadata.
  • MCP Integration: Compatible with MCP clients for LLM context enhancement.
  • DeepSeek Harness (DSH) Integration: A dsh profile bundle (clone the repo, npx @deepseek-ai/[email protected] plugin --profile web add link:./dsh) exposing every tool as mcp__paper-search__*, with an optional guidance skill.
  • Extensible Design: Easily add new academic platforms by extending the academic_platforms module.

Source Strategy

The long-term goal is not to depend on a single search engine, but to combine multiple free and public sources with clear roles:

  • Open metadata backbone: Crossref, OpenAlex, Semantic Scholar, dblp, CiteSeerX, SSRN, Unpaywall (DOI-centric OA metadata).
  • Discipline-specific sources: arXiv, PubMed, PubMed Central, Europe PMC, IACR.
  • Open-access full-text sources: arXiv, PMC, CORE, OpenAIRE, DOAJ, BASE, Zenodo, HAL, publisher open-access links.
  • Discovery and DOI recovery: Google Scholar can be useful for finding titles, versions, and DOI clues when other public metadata sources are incomplete.

Recommended free-first roadmap:

  1. Keep current public sources stable.
  2. Add OpenAlex as a broad free metadata source.
  3. Add PubMed Central and Europe PMC for stronger biomedical full-text access.
  4. Add CORE and OpenAIRE for repository-based open-access retrieval.
  5. Use Google Scholar mainly as a discovery fallback, not as the primary canonical source.

Platform Capability Matrix

This matrix reflects verified live-integration results from functional and end-to-end regression tests in this repository. Columns show the highest capability level observed under normal conditions.

PlatformSearchDownloadReadNotes
arXiv✅✅✅Open API; reliable
PubMed✅❌⚠️ info-onlyOpen API; reliable
bioRxiv✅✅✅Open API; reliable
medRxiv✅✅✅Open API; reliable
Google Scholar⚠️❌❌Upstream bot-detection/rate limits can prevent search; reported as source errors
IACR✅✅✅Open API; reliable
Semantic Scholar✅✅ (OA)✅ (OA)Works without key (rate-limited); key improves limits; key rejection (403) re

// HOW IT'S BUILT

// FILES

2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.

  • claude-code/SKILL.md4.5 KB8593686476d4upstream ↗
    ---
    name: paper-search
    description: Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc). Use when the user asks to find papers, search for research, look up academic literature, download a paper PDF, or extract text from a paper.
    ---
    
    # Paper Search
    
    Search, download, and read academic papers via the `paper-search` CLI.
    
    ## CLI Usage
    
    All commands run via:
    ```bash
    paper-search <command> [args]
    ```
    
    If `paper-search` is not available, install it with `uv tool install paper-search-mcp`. Optional API keys can be configured in `~/.config/paper-search-mcp/.env`.
    
    ### Search
    ```bash
    paper-search search "<query>" -n <max_per_source> -s <sources> -y <year>
    ```
    - `-n`: results per source (default: 5)
    - `-s`: comma-separated sources, "fast", "fastest", or "all" (default: all)
    - `--exhaustive`: compatibility no-op (broad search is already the default); explicit `-s` always takes precedence
    - `-y`: year filter for Semantic Scholar (e.g. "2020", "2018-2022")
    
    For speed, use `-s fast` (OpenAlex, Crossref, arXiv, PubMed, Europe PMC; also Semantic Scholar when its API key is nonblank) or `-s fastest` (OpenAlex and Crossref). Explicit source choices are never expanded, even for DOI queries. Use `-s unpaywall` for DOI lookup; "all" already includes it. These presets do not enable optional paid sources.
    
    ### Download PDF
    ```bash
    paper-search download <source> <paper_id> [-o ./downloads]
    ```
    
    ### Read (extract text)
    ```bash
    paper-search read <source> <paper_id> [-o ./downloads]
    ```
    
    ### List sources
    ```bash
    paper-search sources
    ```
    
    ### MCP tools from the CLI
    
    `paper-search tool` calls the same registered tools as the MCP server, including
    source-specific options and DOI lookup. Required arguments are positional;
    optional arguments use kebab-case flags. Boolean flags use `--flag` and
    `--no-flag`; omitted options retain their MCP defaults.
    
    ```bash
    paper-search tool --help
    paper-search tool --list  # JSON tool list, schemas, and annotations
    paper-search tool search_crossref --help
    paper-search tool search_crossref "transformer attention" --filter from-pub-date:2024-01-01 --sort published --order desc --max-results 2
    paper-search tool get_crossref_paper_by_doi 10.1038/nature12373
    paper-search tool search_iacr "cryptography" --no-fetch-details
    ```
    
    Objects and lists return JSON; text and download paths return plain text. An
    exception returns a JSON error with exit code 1; invalid CLI syntax exits with
    code 2. A normal MCP result retains its original meaning, including error or
    partial-result fields returned by the tool itself. `--list` shows only tools
    enabled by the current configuration, so IEEE tools still require their API
    key. The existing `search`, `download`, `read`, and `sources` commands are
    unchanged. Tool calls keep the MCP tools' source selection and timeout behavior;
    Sci-Hub fallback remains opt-in through `--use-scihub`.
    
    ## Output
    
    `search` and `download` return JSON. `read` returns plain text. Config warnings go to stderr and can be ignored.
    
    ## Sources
    
    arxiv, pubmed, biorxiv, medrxiv, google_scholar, iacr, semantic, crossref, openalex, pmc, core, europepmc, dblp, openaire, citeseerx, doaj, base, zenodo, hal, ssrn, openreview, unpaywall, acm
    
    Optional (env vars): ieee (`IEEE_API_KEY`). ACM search is keyless and uses Crossref metadata; publisher PDF access may require the OA fallback.
    
    Web of Science (`wos`) and Scopus (`scopus`) require their runtime API keys and
    explicit source selection; they are never added to `all`, `fast`, or `fastest`.
    Use `--wos-db` or the `--scopus-view`, `--scopus-sort`, `--scopus-field`, and
    `--scopus-date` options on ordinary search, or inspect their corresponding tool
    help. `read scopus <id>` returns structured abstract metadata; `--full-text`
    explicitly attempts identity-verified article text and returns a nonzero exit
    when full text remains unavailable. An abstract-only result is not full text.
    
    The tool command also exposes `get_citing_papers`, `get_referenced_papers`,
    `get_search_cache_status`, and `clear_search_cache`. Relationship lookups accept
    DOIs/OpenAlex IDs, with bounded one-hop retrieval. Caching is off by default;
    enabling it persists queries and public results, and requires an explicit
    operator choice. Clearing the search cache does not remove downloaded PDFs.
    
    ## Workflow
    
    1. Search with targeted sources to find papers
    2. Present results as a table: title, authors, year, source, DOI/URL
    3. If the user wants full text, use `read <source> <paper_id>`
    4. If the user wants the PDF, use `download <source> <paper_id>` and report the saved path
    
  • README.mdupstream ↗

    Contents are not inlined in the catalog. Open the upstream file.

Plain-text copy, no login: /skill-bundles/openags-paper-search-mcp-claude-code.md

// REPO STATS

3.1k stars
11 open issues
Last commit: 1mo ago