Search & Research MCP Servers

MCP server for OpenAI o3 web search

Google search with parallel queries for multiple keywords.

Web search with quality scores; web pages are read on your computer by the local server.

Multi-engine search and deep research for AI agents across 300+ sources, 18 languages, and MCP / CLI.

Fast MCP server for unified SAP docs search (SAPUI5, CAP, OpenUI5, wdi5) with BM25 full-text search

An MCP server for academic paper search that integrates with AI assistants (e.g., Claude Code, Cursor), enabling them to search and…

Unsplash image search.

Fast discovery search and self-hosted web research for MCP agents.

Parse PDFs, images, doc, docx, ppt, pptx, xls, xlsx, html into Markdown using MinerU API.

MCP server for ITASCA PFC, FLAC3D, 3DEC, MPoint and MassFlow: search docs, run simulations, plot.

Gemini 3 MCP server with 30+ tools: images, video, research, TTS, code exec & CLI

Autonomous deep research with structured query elaboration and concise reporting.

On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.

USPTO patent creation system with MCP server + Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, BigQuery access to 76M+ patents,…

Local search of foods, nutrition facts and barcodes in the OpenNutrition database.

Search and read papers from arXiv.

Interact & query with Meilisearch (Full-text & semantic search API)

A free SEO research tool using Model Context Protocol (MCP) powered by Ahrefs data. Get backlink analysis, keyword research, traffic…

A Node.js implementation of the Model Context Protocol (MCP) server for searching and downloading academic papers from multiple sources,…

Web search via SearXNG and/or You.com, plus clean Markdown crawling via Crawl4AI. Self-hosted.

Free MCP server for web search powered by Google AI Mode (Gemini). Unlimited, no API key.

Extract content from web pages, PDFs, Word documents, YouTube transcripts, audio and video with automatic engine selection and structured…

Official SerpApi MCP server for Google, Bing, and other search engines.

Data extraction with AgentQL.

Checks every LaTeX reference against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex. No LLM.

No-API-key web search, page fetching and document reading across many engines. Local-first.

Multi-engine web and platform search, news, Google Maps places, page reading, sitemaps, and trends.

Search and read medical and life sciences papers from PubMed.

Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.

Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.

Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms.

A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information,…

Convert websites to clean Markdown with links preserved, using Mozilla Readability, caching, robots.txt-aware crawling and concurrent…

Chromium-free web content extraction in a single binary: fetch, render, crawl and screenshot pages with the Servo browser engine.

Connect AI assistants to Outline for document search, reading, and management

Semantic search and pattern discovery for Obsidian and markdown vaults.

Open Source MCP Servers for Scientific Research

Local web search with multi-engine deep research and on-device re-ranking. No API keys.

Get the LaTeX source of arXiv papers to handle mathematical content and equations.

A PubMed MCP server.

Web search, URL discovery, scraping & extraction with agent-browser and search providers

ReActMCP is a reactive MCP client that empowers AI assistants to instantly respond with real-time, Markdown-formatted web search insights…

Deterministic research MCP server on FastMCP 3 — 5-engine web search, 9-platform social search, 6 academic DBs, news aggregation, entity…

🔎 One query. Three search engines. Self-hosted web search for AI agents via HTTP API or MCP. Aggregates DuckDuckGo, Brave & Yahoo. Built…

Your Obsidian vault, exposed to Claude, Codex, Cursor and any MCP client. Runs inside Obsidian, on-device semantic search, no cloud…

🔍 Enable AI assistants to search, access, and analyze PubMed articles through a simple MCP interface.

Connect to SearXNG instances.

Google News via SerpAPI: search headlines, stories and related topics, with automatic topic categorization and multi-language support.

A Model Context Protocol (MCP) server providing AI assistants with access to healthcare data and medical information tools, including FDA…

Web, image, news, video and local point-of-interest search using Brave's Search API.

Git for AI Agent Knowledge. A persistent, versioned memory layer for AI systems. Hybrid GraphRAG retrieval. Runs entirely offline.

Search Obsidian vaults with hybrid full-text, fuzzy, semantic, and graph retrieval.

A MCP server for PubMed data

Search and read the docs and examples of react-three-fiber, drei, zustand, jotai... from your agent

Academic Paper Search MCP Server for Claude Desktop integration. Allows Claude to access data from Semantic Scholar and Crossref.

Deep research via the OpenAI Responses API or Open Deep Research (smolagents), with web search and code interpreter support.

Retrieval, private deep research, file-to-Markdown extraction and text chunking via Vectorize.

Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.

Capture website screenshots, tiling full pages into 1072x1072 chunks for Claude Vision, with configurable viewports and wait strategies…

豆包搜索 MCP server — 给换了国产模型的 Claude Code 补上联网能力。字节系信源、千字正文、每月500次免费 | Agent-first web search MCP