paper-search-mcp-gateway

paper-search-mcp-gateway

FastMCP gateway that exposes paper-search-mcp as an HTTP MCP server, enabling search and download of academic papers from arXiv, PubMed, bioRxiv, medRxiv, and Google Scholar.

Category
Visit Server

README

Paper Search MCP Gateway

FastMCP gateway that exposes paper-search-mcp as an HTTP MCP server.

Soporta búsqueda y descarga de papers académicos desde arXiv, PubMed, bioRxiv, medRxiv y Google Scholar.

Tools disponibles

Tool Descripción
papers_search_arxiv Busca en arXiv
papers_search_pubmed Busca en PubMed
papers_search_biorxiv Busca en bioRxiv
papers_search_medrxiv Busca en medRxiv
papers_search_google_scholar Busca en Google Scholar
papers_download_arxiv Descarga PDF de arXiv
papers_download_biorxiv Descarga PDF de bioRxiv
papers_download_medrxiv Descarga PDF de medRxiv
papers_read_arxiv_paper Lee texto de un paper de arXiv

Variables de entorno

Variable Default Descripción
TRANSPORT http Transporte MCP: http, sse, stdio
HOST 0.0.0.0 Host donde escucha el servidor
PORT 8000 Puerto donde escucha el servidor
SEMANTIC_SCHOLAR_API_KEY (vacío) API key opcional de Semantic Scholar

Copia .env.example a .env y edita los valores.

Desarrollo local

uv sync
uv run python main.py

El servidor queda disponible en http://localhost:8000/mcp.

Docker

docker build -t paper-search-gateway .
docker run -p 8000:8000 --env-file .env paper-search-gateway

Despliegue en Dokploy

  1. Conecta el repositorio en Dokploy → New Application → GitHub
  2. Selecciona Dockerfile como método de build
  3. Añade las variables de entorno en Environment Variables:
    • TRANSPORT=http
    • PORT=8000
    • SEMANTIC_SCHOLAR_API_KEY= (opcional)
  4. Expón el puerto 8000
  5. El endpoint MCP quedará en: https://tu-dominio.com/mcp

Conectar desde un cliente MCP

{
  "mcpServers": {
    "papers": {
      "url": "https://tu-dominio.com/mcp",
      "transport": "http"
    }
  }
}

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured