papers-mcp
This server provides scientific grounding by enabling search, discovery, and retrieval of research papers across multiple scholarly sources (arXiv, OpenAlex, Crossref, PubMed, and Semantic Scholar). Key capabilities:
Search papers (
search_papers): Aggregate search with filters for year range, source, open-access only, sorting, and result limit. Returns a unified schema including title, authors, abstract, DOI, citation count, open-access status, and retraction flag.Resolve paper details (
get_paper): Retrieve full metadata, references (even for paywalled journals), and citations by DOI, arXiv ID, PMID, OpenAlex ID, or S2 ID. Optional liveness and retraction verification.List sources (
list_sources): View available scholarly sources, their coverage, requirements, and rate limits.Methodology guide (
get_research_method): Access recommended research methodology, including tool tiers, interpretation rules, source quirks, and verification steps.Graceful degradation: Failing or rate-limited sources are skipped and reported.
Optional Semantic Scholar API key lifts rate limits; anonymous telemetry (opt-out) collects usage events, never storing queries or content.
Retrieve metadata, references, and citations from ACM publications even when the full text is paywalled.
Aggregated search for open-access preprints across computer science, physics, mathematics, and more.
Retrieve metadata, references, and citations from Elsevier publications even when the full text is paywalled.
Retrieve metadata, references, and citations from IEEE publications even when the full text is paywalled.
Search biomedical citations and access free full-text from PubMed/PMC.
Search a large corpus of scholarly papers with citation graph and TLDRs.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@papers-mcpsearch for papers about CRISPR gene editing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Scientific Research Papers MCP Server 📄
Scientific literature grounding MCP server for AI agents: unified search across 250M+ scholarly papers on arXiv, PubMed, OpenAlex, CrossRef, and Semantic Scholar.
🌐 Live Documentation & Web Portal: https://papers.builditwithai.xyz
⚡ Quickstart
# 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-mcpRelated MCP server: Academic Paper MCP HTTP/SSE Server
🤖 Client Setup
A. Claude Code (CLI)
claude mcp add papers -- uvx find-research-papers-mcpB. Cursor & Google Antigravity (mcp.json)
{
"mcpServers": {
"papers": {
"command": "uvx",
"args": ["find-research-papers-mcp"]
}
}
}C. Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"papers": {
"command": "uvx",
"args": ["find-research-papers-mcp"]
}
}
}D. VS Code (Cline / Roo Code / Continue)
{
"mcpServers": {
"papers": {
"command": "npx",
"args": ["-y", "find-research-papers-mcp"]
}
}
}🛠️ Tools & Capabilities
Tool Name | Parameters | Description | Return Type |
|
| Unified multi-index search across arXiv, PubMed, OpenAlex, CrossRef, Semantic Scholar. |
|
|
| Retrieves paper metadata, abstract, authors, publication date, and open-access PDF link. |
|
|
| Fetches complete bibliography and referenced papers via CrossRef. |
|
|
| Fetches citing papers and citation graph via OpenAlex. |
|
|
| HEAD-checks landing page accessibility and cross-checks retraction databases. |
|
| (none) | Returns live status and latency metrics for all 5 scholarly indexes. |
|
|
| Dynamically loads research methodology skills from GitHub. |
|
| (none) | Lists all available scientific research skills. |
|
🔒 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:
export DO_NOT_TRACK=1
# or
export MCP_TELEMETRY_OPT_OUT=1📄 License
MIT License. See LICENSE for details.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server enabling AI agents to search and retrieve scientific papers, citations, and author profiles from Crossref, OpenAlex, and Semantic Scholar with no API keys required.53MIT
- AlicenseNot gradedqualityDmaintenanceA MCP server for academic literature retrieval, aggregating multiple data sources like arXiv, Crossref, OpenAlex, PubMed, and Semantic Scholar to provide search, details, citations, trends, and recommendations.4MIT
- AlicenseAqualityAmaintenanceA FastMCP server for the scholarly citation landscape that enables LLMs to search, cross-reference, and retrieve prior art across papers, patents, books, and standards via multiple APIs.222MIT
- AlicenseAqualityCmaintenanceUnified MCP server for scientific literature search and extraction, integrating databases like Scopus, OpenAlex, Semantic Scholar, and Unpaywall to enable AI agents to discover papers, track citations, and analyze content.27MIT
Related MCP Connectors
Academic research MCP server for paper search, citation checks, graphs, and deep research.
Scholarly search: OpenAlex, Crossref, arXiv, OpenCitations and PubMed in one endpoint.
Read-only MCP over an agentic SLR workspace with per-claim citation verification
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/surendranb/find-research-papers-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server