MCPs for web search, semantic search, and retrieval
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.
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.
Paste a research topic in Notion and an agent uses Perplexity to gather sources, summarize findings, and structure them.
Run Tavily searches on scheduled topics and index the results in Supabase for trend analysis and content research.
Keep Meilisearch in sync with your Supabase tables. Inserts, updates, and deletes are reflected in the search index in real time.
Run daily Perplexity searches on competitors and log product updates, pricing changes, and news to a Notion tracker.
Tavily and Perplexity are the two strongest options. Tavily is more API-like (JSON results); Perplexity returns synthesized answers with citations.
Yes — Pinecone, Weaviate, or pgvector on Postgres. The MCP handles embedding + querying; you provide the store.
Absolutely. A common pattern is: Tavily (web) + Meilisearch (internal docs) + Pinecone (semantic). The agent picks the right tool per query.
Tavily indexes updates within minutes for major sites. Perplexity hits Google's live index. Both are fresher than an LLM's training cutoff.
Browse the full marketplace or explore all tags to find the right MCPs for your stack.