# Semantic Search

> Browse 34 items tagged with Semantic Search.

## Items

- [Microsoft Learn Docs MCP Server](https://mcpserver.ever.works/th/items/microsoft-learn-docs-mcp-server) — Cloud-hosted MCP server providing AI assistants with real-time access to official Microsoft documentation through semantic search. It connects to the Microsoft Learn API endpoint and enables contextual search across Azure docs, .NET/C# documentation, Microsoft 365 resources, and other official Microsoft technical sources.
- [Exa AI MCP Server](https://mcpserver.ever.works/th/items/exa-ai-mcp-server) — MCP server connecting AI models to Exa AI's neural semantic search API, enabling safe, up-to-date web searches across diverse sources including academic papers, company data, LinkedIn, Wikipedia, and GitHub with research-optimized semantic understanding.
- [Exa AI Search MCP](https://mcpserver.ever.works/th/items/exa-ai-search-mcp) — A neural semantic search MCP server that connects AI models to the Exa AI Search API, enabling intelligent searches across academic papers, company data, LinkedIn, Wikipedia, GitHub, and more with AI-optimized semantic understanding.
- [CodeWeaver MCP Server](https://mcpserver.ever.works/th/items/codeweaver-mcp-server) — Full-stack Model Context Protocol platform for semantic code navigation using natural language queries with support for multiple embedding providers (Voyage AI, OpenAI, Cohere, HuggingFace) and vector databases (Qdrant, Pinecone, Weaviate, ChromaDB).
- [Weaviate MCP Server](https://mcpserver.ever.works/th/items/weaviate-mcp-server) — Official Weaviate vector search MCP server enabling AI agents to interact with Weaviate vector database through hybrid search, semantic search, and keyword search capabilities via the Model Context Protocol.
- [Vectara RAG MCP Server](https://mcpserver.ever.works/th/items/vectara-rag-mcp-server) — Vectara-MCP provides agentic applications with fast, reliable RAG through the Model Context Protocol. Leverages Vectara's Trusted RAG platform with semantic search, hallucination detection, and grounded generation capabilities.
- [Pinecone MCP Server](https://mcpserver.ever.works/th/items/pinecone-mcp-server) — MCP server built on Pinecone’s vector database for fast, similarity-based context retrieval optimized for LLMs recalling semantically relevant facts or documents.
- [Vectara MCP Server](https://mcpserver.ever.works/th/items/vectara-mcp-server) — Commercial MCP server designed for semantic search and retrieval-augmented generation (RAG). Enables real-time, relevance-ranked context delivery to LLMs using custom and domain-specific embeddings. Supports multi-language queries and is API-first.
- [Fuel MCP Server](https://mcpserver.ever.works/th/items/fuel-mcp-server) — Facilitates seamless IDE integration with Fuel Network and Sway Language documentation through advanced semantic search capabilities.
- [chroma-mcp](https://mcpserver.ever.works/th/items/chroma-mcp) — A server providing data retrieval capabilities powered by the Chroma embedding database, enabling AI models to create and retrieve data collections using vector search, full text search, and metadata filtering.
- [Qdrant MCP Server for Semantic Search](https://mcpserver.ever.works/th/items/qdrant-mcp-server-for-semantic-search) — Model Context Protocol server providing semantic search capabilities using local Qdrant vector database with support for multiple embedding providers including Ollama, OpenAI, Cohere, and Voyage AI for intelligent information retrieval.
- [Qdrant MCP Server](https://mcpserver.ever.works/th/items/qdrant-mcp-server-qdrant) — Qdrant MCP server for vector similarity search and storage. Features high-performance vector database with semantic search, filtering, and recommendations. Ideal for AI/ML applications requiring fast vector operations.
- [Qdrant MCP Server](https://mcpserver.ever.works/th/items/qdrant-mcp-server) — Qdrant MCP Server integrates Qdrant's vector database with MCP for semantic search and similarity matching in AI workflows. It supports vector embeddings, collections management, and hybrid search combining dense and sparse vectors. Ideal for RAG pipelines, recommendation systems, and knowledge retrieval in agents; offers an open-source, self-hosted alternative to Pinecone MCP.
- [memory-box-mcp](https://mcpserver.ever.works/th/items/memory-box-mcp) — Cline MCP integration for Memory Box - save, search and format memories with semantic understanding. Useful for databases, search, and knowledge management.
- [Perplexity MCP](https://mcpserver.ever.works/th/items/perplexity-mcp) — Semantic search MCP for finding relevant sources on topics.
- [Vector Search MCP Server](https://mcpserver.ever.works/th/items/vector-search-mcp-server) — MCP server for semantic data search enabling embedding processing, similarity matching, and data partitioning. Setup involves environment variables, embedding model, and collection creation, with integration support for various embedding models.
- [fooddb](https://mcpserver.ever.works/th/items/fooddb) — Query USDA Food Data Central with smart keyword and semantic vector search capabilities.
- [openMM-Doc-MCP](https://mcpserver.ever.works/th/items/openmm-doc-mcp) — Facilitates semantic search through OpenMM molecular dynamics documentation using vector embeddings and FAISS for efficient retrieval, optimized for LLM integration.
- [central-intelligence](https://mcpserver.ever.works/th/items/central-intelligence) — Persistent memory for AI agents with five tools: remember, recall, context, forget, share. Features semantic search via vector embeddings and scoping for agent/user/org. Compatible with Claude Code, Cursor, Windsurf, and any MCP client.
- [Exa MCP Server](https://mcpserver.ever.works/th/items/exa-mcp-server) — AI-friendly search returning structured, semantically relevant results designed for agent consumption. Step up from generic search for research workflows.
- [memora](https://mcpserver.ever.works/th/items/memora) — Persistent memory with knowledge graph visualization, semantic/hybrid search, cloud sync (S3/R2), and cross-session context management for AI agents.
- [memory-nexus-cloud](https://mcpserver.ever.works/th/items/memory-nexus-cloud) — Cloud-hosted persistent semantic memory for AI agents with semantic search, knowledge graphs, specialist expertise hats, and multi-tenant isolation. Offers a free 7-day trial.
- [Fast.io MCP Server](https://mcpserver.ever.works/th/items/fastio-mcp-server) — MCP server that treats file storage as a queryable database, indexing the content and context of files including contracts, video assets, design files, and PDFs. Enables semantic search and built-in RAG for unstructured data without requiring a separate vector database.
- [Google Vertex AI Search](https://mcpserver.ever.works/th/items/google-vertex-ai-search) — Provides Google Vertex AI Search results by grounding a Gemini model with your own private data. Enables AI agents to perform semantic search across enterprise data using Google's Vertex AI platform.
- [MCP Obsidian Index](https://mcpserver.ever.works/th/items/mcp-obsidian-index) — MCP server providing semantic search over Obsidian vaults, enabling AI assistants to perform intelligent searches across personal knowledge bases stored in Obsidian.
- [Meilisearch](https://mcpserver.ever.works/th/items/meilisearch) — MCP server for interacting with Meilisearch full-text and semantic search API, enabling AI agents to perform fast, relevant searches on indexed content.
- [Milvus](https://mcpserver.ever.works/th/items/milvus) — MCP server for searching, querying, and interacting with data in Milvus Vector Database, enabling AI agents to perform vector similarity searches.
- [RAG Retriever](https://mcpserver.ever.works/th/items/rag-retriever) — Python application that loads and processes both web pages and local documents, indexing content using embeddings and enabling semantic search queries through MCP.
- [YouTube AI MCP Server](https://mcpserver.ever.works/th/items/youtube-ai-mcp-server) — An AI-powered YouTube solution that enables users to search for videos, retrieve detailed transcripts, and perform semantic searches over video content without relying on the official YouTube API, using vector database integration for streamlined content discovery.
- [Zilliz Milvus MCP Server](https://mcpserver.ever.works/th/items/zilliztech-milvus-mcp) — Model Context Protocol Servers for Milvus vector databases by zilliztech. Enables LLMs to interact with Milvus for semantic search, similarity matching, and vector database operations through MCP.
- [LanceDB MCP Server](https://mcpserver.ever.works/th/items/lancedb-mcp-server) — Embedded vector database MCP server providing local, zero-config vector storage and similarity search operations using LanceDB for efficient semantic search and AI-powered applications.
- [Milvus MCP Server](https://mcpserver.ever.works/th/items/milvus-mcp-server) — Official Model Context Protocol server for Milvus vector database enabling AI assistants to search, query, and interact with vector data for semantic search and similarity matching applications.
- [CodeGraphContext](https://mcpserver.ever.works/th/items/codegraphcontext) — CodeGraphContext is an MCP server that indexes local code into a graph database, exposing structured code context to AI assistants. It enables graph-based code exploration and reasoning for coding agents via the MCP protocol.
- [alibabacloud-tablestore-mcp-server](https://mcpserver.ever.works/th/items/alibabacloud-tablestore-mcp-server) — MCP server implementation for Alibaba Cloud Tablestore, supporting document management, semantic and vector search, RAG-friendly, and serverless capabilities.

---

_Canonical page: https://mcpserver.ever.works/th/tags/semantic-search_