Search open-source research papers across arXiv, OpenAlex, Crossref, PubMed, Semantic Scholar.
io.github.surendranb/find-research-papers-mcp — MCP Server
This Model Context Protocol (MCP) server provides unified search for open-source scientific research papers across arXiv, OpenAlex, Crossref, PubMed, and Semantic Scholar. It is intended for AI agents that need access to scholarly literature from multiple sources.
🛠️ Key Features
Search open-source research papers across arXiv, OpenAlex, Crossref, PubMed, and Semantic Scholar
Scientific literature grounding MCP server for AI agents: unified search across 250M+ scholarly papers on arXiv, PubMed, OpenAlex, CrossRef, and Semantic Scholar.
# 1-Line Universal Installer (Auto-configures Claude Desktop, Cursor, Claude Code, Antigravity, VS Code, Zed, Windsurf)
curl -fsSL "https://papers.builditwithai.xyz/install" | bash
# Or run directly via your preferred runtime:
uvx find-research-papers-mcp
npx -y find-research-papers-mcp
🤖 Client Setup
A. Claude Code (CLI)
bash
claude mcp add papers -- uvx find-research-papers-mcp
Unified multi-index search across arXiv, PubMed, OpenAlex, CrossRef, Semantic Scholar.
JSON / Markdown
get_paper
doi (string) or id (string)
Retrieves paper metadata, abstract, authors, publication date, and open-access PDF link.
JSON
get_references
doi (string)
Fetches complete bibliography and referenced papers via CrossRef.
JSON
get_citations
doi (string)
Fetches citing papers and citation graph via OpenAlex.
JSON
verify_paper
doi (string)
HEAD-checks landing page accessibility and cross-checks retraction databases.
JSON
list_sources
(none)
Returns live status and latency metrics for all 5 scholarly indexes.
JSON
skill_read
skill_name (string)
Dynamically loads research methodology skills from GitHub.
Markdown
skills_list
(none)
Lists all available scientific research skills.
JSON
🔒 Telemetry & Privacy
This package collects anonymous, non-PII diagnostic telemetry (command executions, latency, error codes) to improve tool reliability. No research queries, paper results, personal data, source code, or environment variables are ever collected or stored.
You can opt out anytime by setting either of the following environment variables:
