mcpField
F
Find Research Papers

Find Research Papers

Local
github.com/surendranbSearch7Updated today
Repository

About Find Research Papers

Find Research Papers is an MCP server for searching scholarly literature across arXiv, PubMed, OpenAlex, Crossref, and Semantic Scholar. Research agents can retrieve paper metadata, references, citations, and access or retraction checks.

Key features

  1. 01Search five scholarly indexes
  2. 02Retrieve metadata, abstracts, and PDF links
  3. 03Fetch references and citing papers
  4. 04Check accessibility and retraction status
  5. 05List index status and latency
  6. 06Load research methodology skills

Use cases

  1. 01Find papers across multiple indexes
  2. 02Inspect a paper's abstract and authors
  3. 03Trace references and citation links
  4. 04Check a paper's accessibility or retraction status

MCP support

The server exposes literature search, paper retrieval, citation and reference lookup, verification, and research-skill tools to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "surendranb-find-research-papers": {
      "command": "uvx",
      "args": [
        "find-research-papers-mcp"
      ],
      "env": {
        "FIND_RESEARCH_PAPERS_MCP_S2_API_KEY": "<FIND_RESEARCH_PAPERS_MCP_S2_API_KEY>"
      }
    }
  }
}
Run commanduvx find-research-papers-mcp
Environment variables to set
FIND_RESEARCH_PAPERS_MCP_S2_API_KEYSecretSemantic Scholar API key. Without it, the shared rate pool may 429 (source is skipped, never a crash).

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypifind-research-papers-mcp0.4.9

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

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.

CI PyPI version npm version OpenSSF Scorecard License: MIT

🌐 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-mcp

🤖 Client Setup

A. Claude Code (CLI)
claude mcp add papers -- uvx find-research-papers-mcp
B. 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 NameParametersDescriptionReturn Type
search_papersquery (string), sources (list), limit (int)Unified multi-index search across arXiv, PubMed, OpenAlex, CrossRef, Semantic Scholar.JSON / Markdown
get_paperdoi (string) or id (string)Retrieves paper metadata, abstract, authors, publication date, and open-access PDF link.JSON
get_referencesdoi (string)Fetches complete bibliography and referenced papers via CrossRef.JSON
get_citationsdoi (string)Fetches citing papers and citation graph via OpenAlex.JSON
verify_paperdoi (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_readskill_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:

export DO_NOT_TRACK=1
# or
export MCP_TELEMETRY_OPT_OUT=1

📄 License

MIT License. See LICENSE for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.