🔍
Tag8 MCPs tagged here

Search & Retrieval

MCPs for web search, semantic search, and retrieval

TL;DR

Search MCP servers give agents access to web search, full-text search, and vector retrieval. They combine freshness (real-time web), recall (full-text), and semantic understanding (embeddings) into tools agents can mix and match. Central to RAG pipelines.

About Search & Retrieval

Search MCPs connect agents to live web search (Google, Tavily, Perplexity), internal document search (Meilisearch, Elastic, Typesense), and semantic vector search. They're the foundation of any RAG or research pipeline.

Common use cases

  • Let an agent search the current web (not just its training data)
  • Full-text search across internal company documents
  • Semantic search over product catalogs, support tickets, or codebases
  • Hybrid search: combine keyword + vector for best recall/precision
  • Power 'ask your data' UIs with Meilisearch or Typesense

Frequently asked questions

What's the best web search MCP?

Tavily and Perplexity are the two strongest options. Tavily is more API-like (JSON results); Perplexity returns synthesized answers with citations.

Do I need a vector database for semantic search?

Yes — Pinecone, Weaviate, or pgvector on Postgres. The MCP handles embedding + querying; you provide the store.

Can I combine multiple search MCPs?

Absolutely. A common pattern is: Tavily (web) + Meilisearch (internal docs) + Pinecone (semantic). The agent picks the right tool per query.

How fresh is web search data?

Tavily indexes updates within minutes for major sites. Perplexity hits Google's live index. Both are fresher than an LLM's training cutoff.

Install Search & Retrieval MCPs

Browse the full directory or explore all tags to find the right MCPs for your stack.