"A server for searching and retrieving information using keyword, semantic, or hybrid search methods" matching MCP servers:

MCP server that indexes Obsidian notes and enables hybrid search (full-text, fuzzy, semantic) for AI assistants to find and read notes.

Enables fully local semantic search over a Roam Research graph via MCP, providing tools for hybrid retrieval, index refresh, and stats while keeping all content on-machine.

Local offline semantic search over documents (txt, md, pdf, docx, pptx, csv). Indexes folders into a LanceDB vector database with multilingual embeddings and supports hybrid vector + keyword search via Reciprocal Rank Fusion. No API keys, no cloud, no Docker required.

Local semantic recall MCP server for citation-integrity workflows. Enables semantic search over a text corpus, returning file paths and page numbers for verification, with 100% local processing using ONNX embeddings and LanceDB.

A tiny RAG-lite retrieval engine that indexes files on disk and provides semantic search via MCP, returning relevant text chunks (file, line, score) without generating answers.

Enables semantic code search over local repositories, providing tools like semantic_search and list_indexed_repos to Claude Code, so users can find relevant code sections via natural language instead of grep.

Enables semantic search over documentation stored in a Vectorize database using the Cloudflare Agents SDK, allowing users to query indexed content via natural language.

A local MCP server enabling hybrid search over documents, memory, and knowledge graphs for retrieval-augmented generation, with tools for SQLite, semantic memory, and entity-relationship queries.

A Python MCP server that enables semantic search through Search Labs blog posts indexed in Elasticsearch, allowing Claude to intelligently retrieve relevant information from the blog content.

Enables semantic search over local notes and documents using natural language queries. Supports multiple file types (Markdown, Python, HTML, JSON, CSV, text) with fast local embeddings and persistent ChromaDB vector storage.

Enables semantic search over local markdown specs, RFCs, and docs using Ollama and LanceDB, allowing AI agents to find relevant information by meaning rather than exact keywords.

Read-only semantic retrieval for agents that need to find the right Obsidian note without write access.

Enables hybrid retrieval-augmented generation with semantic and keyword search over documents, supporting multiple formats and providing MCP integration for Claude Desktop.

An unofficial MCP server that provides semantic search capabilities for Hugging Face models and datasets, enabling Claude and other MCP-compatible clients to search, discover, and explore the Hugging Face ecosystem using natural language queries.

Enables AI agents to use a hybrid dense+sparse RAG system with tag-based long-term memory (importance, knowledge-type decay, access-frequency boost) via MCP tools for document ingestion, hybrid search, staged reranking, forgetting, and index management.

A modular Retrieval-Augmented Generation (RAG) framework that provides hybrid search and knowledge retrieval capabilities via the Model Context Protocol. It enables users to integrate document-based knowledge into LLM workflows with support for dense/sparse retrieval, reranking, and observability.

Enables Claude to perform hybrid search across local documents by combining semantic vector retrieval and BM25 keyword matching for optimal context recovery. It supports multiple file formats including PDF, CSV, and Markdown, leveraging local Ollama models for private and efficient document querying.

A local semantic search MCP server for Markdown vaults that indexes and retrieves notes using hybrid keyword and embedding search.

Universal FastMCP bridge into a hybrid memory stack, enabling MCP-capable agents to save, search, read, and recall memories using OpenViking and Honcho backends.

An MCP server that provides a search_docs tool with hybrid retrieval (BM25 + dense vectors) and cross-encoder reranking, backed by evaluation, prompt-injection guardrails, and OpenTelemetry tracing.