Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.
AI Catholic formation — spiritual direction, saints, scripture, and semantic search.
Local-first bookmark management with semantic search and AI-powered organization.
Semantic search knowledge base with serverless LanceDB. Zero setup, 100% local, 25+ file types.
MantisBT MCP server – manage issues, notes, files, tags, and relationships. With semantic search.
Read-only answers and semantic search for wiki.private.law, served by the Mothership runtime.
Semantic search over 50,000+ Dynamics 365 F&O artifacts: tables, forms, classes, and more.
Russian-language web search for agents: hybrid retrieval, product prices, full page text.
Semantic search through Dickens' A Christmas Carol by meaning, theme, or character.
Summarized Bulgarian news from leading outlets: semantic search, top stories, article summaries.
Search the web in real time to get trustworthy, source-backed answers.
Local repo context for coding assistants with semantic search and graph relationships.
{GIN} verdict, M-Value AVM, market facts + semantic search for Moroccan real estate. Moat-safe.
MCP server for advanced web search using Tavily API.
Quran Search Engine MCP for AI tools. Provides Quran search, Arabic normalization, and highlighting.
MCP server for SearXNG aggregator — web search across multiple engines via Model Context Protocol.
Google & Yandex SERP, image/news verticals and URL indexation checks via XMLRiver (read-only).
Google & Yandex SERP + Yandex Wordstat via XMLStock (read-only).
Google/Yandex SERP parsing and Yandex Wordstat keyword frequency via XMLRiver XML API.
Calibre ebook library server: search, read content, curate metadata, semantic search, gated writes.
An MCP server that validates content against MCP specification using semantic search and AI.
MCP server exposing Exa websearch API.
Real-world data for agents: air quality, geocoding, quakes, holidays, web search.
Local-first second brain with semantic search. Markdown notes indexed by a local ML model.
About Search MCP servers
Search servers answer the question most assistants cannot on their own: what is true right now. They expose tools for web search, news, academic and code search, site-specific search and content extraction, returning ranked results or cleaned page text the model can cite. Some are built for agents from the start, with structured results and relevance tuned for follow-up questions rather than ten blue links.
Most search servers are hosted and need an API key with usage-based pricing, so check rate limits and what a free tier includes. Look at whether results come back with source URLs and dates, whether the server can fetch and summarise full pages, and how it handles regional or language settings. Pair a search server with a scraping server when you need deeper extraction.