# Semantic search

A system integrating the Qdrant vector database and MCP server for storing and retrieving code snippets, supporting natural language search and semantic retrieval.

A lightning-fast, language-agnostic code analysis MCP server built on Rust, offering instant symbol lookup, reference tracking, and semantic code search. Designed for large codebases with performance as a priority.

CICADA is an MCP server that provides structured code indexing for AI code assistants. Through AST-level indexing, call site tracking, and semantic search, it provides efficient context compression for Elixir, Python, and Erlang code repositories, reducing token usage and improving the quality of code understanding.

Claude Context is an MCP plugin that provides in - depth context of the entire codebase for AI programming assistants through semantic code search. It supports multiple embedding models and vector databases to achieve efficient code retrieval.

Glider is a Roslyn-based MCP server that provides semantic analysis, intelligent refactoring, and architecture exploration capabilities for C# code in MCP clients (such as Claude Code).

This is an MCP server designed for the Smart Connections plugin, providing read-only semantic search functionality for the Obsidian knowledge base, emphasizing security and lightweight implementation.

Memory MCP is an MCP server that provides persistent memory for AI assistants. Through a two - tier architecture of hot cache and cold storage, it enables zero - latency automatic injection of high - frequency knowledge and semantic search, allowing Claude to remember project contexts and reduce repeated explanations.

Criterion is an AI - based Islamic knowledge assistant that provides authoritative guidance through the Quran and Hadith. It uses semantic search and real - time streaming response technology, is permanently free, and focuses on core doctrines.

This project is a semantic search tool based on Elasticsearch for semantic retrieval of Search Labs blog posts, including crawler configuration, index mapping updates, and MCP server integration functions.

A lightweight Model Context Protocol (MCP) server that provides localized vector storage and database management to implement persistent memory and context management functions for AI assistants.

mc-mcp is an MCP server designed for the metacontract framework, providing support for smart contract development, including semantic document search, Foundry integration, and contract deployment.

The MCP-RAG Server is an implementation based on the Model Context Protocol (MCP), aiming to provide real-time document access to AI assistants through semantic vector search, thereby generating context-aware responses based on the latest information.

The mem0 MCP Server provides structured memory storage and semantic search services for project management

CodeFlow is an intelligent code analysis tool that generates detailed call graphs by parsing the abstract syntax tree of the code and provides semantic search functionality. It includes two interfaces, a CLI tool and an MCP server, aiming to help developers understand complex codebases with minimal cognitive burden.

Context Lens is a local semantic search tool that can convert any content into a searchable knowledge base, enabling AI assistants to understand the meaning rather than just match keywords. It uses a built - in LanceDB vector database, supports local files, GitHub repositories, and URL content, does not require an API key or cloud service, and processes data completely locally.

A high-performance MCP server that provides persistent multimodal context storage for LLM agents, supports thread isolation, metadata filtering, full-text search, and semantic search, and is compatible with SQLite and PostgreSQL backends.

A local vector database MCP server based on FAISS, providing document embedding, semantic search, and RAG functions, supporting multiple document formats and custom embedding models.

pg-aiguide is an AI-optimized PostgreSQL knowledge base that provides semantic search for official documentation, best practice skills, and extended ecosystem documentation for AI programming assistants, helping to generate higher-quality PostgreSQL code.

The Smart Coding MCP server provides a semantic - based code search function for coding assistants through a local AI model, supporting multi - project management and progressive indexing.

JitAPI is an MCP server that enables LLMs to interact with any API by dynamically discovering relevant endpoints in the OpenAPI specification. It uses semantic search and dependency graphs to find only the endpoints required for each task, supporting multi-API registration, LLM-driven workflow planning, and general execution.

DeepZotero is a tool that provides semantic search functionality for the Zotero literature library. It extracts text, tables, and images from PDFs, chunks, embeds, and stores them in ChromaDB. Finally, it provides 13 types of semantic search, Boolean search, table/image search, context expansion, citation graph query, index management, and cost - tracking tools to clients such as Claude Code through the MCP server.

markymark is a language server and AI agent tool for Markdown and structured data files, providing navigation, refactoring, search, and diagnostic functions, and supporting the LSP and MCP protocols.

A local server based on the MCP protocol that implements semantic search and RAG functions for Apple Notes, which can be called by AI assistants such as Claude.

This project provides a set of toolkits for crawling website content and generating Markdown documents. At the same time, it realizes the semantic search function of documents through the MCP server and supports integration with tools such as Cursor.

An MCP service for semantic search of Apple Notes, supporting local embedding models, full-text search, and vector storage.

A Python - based service application that provides functions for getting metadata from SharePoint and retrieving entities from the Neo4j knowledge graph through semantic similarity search.

This is an MCP service that provides a free public API directory, supports semantic search and detailed API information queries, and is built on a public API dataset.

Engram is an event - sourcing memory system designed for AI agents, adopting an architecture without an LLM write path, and achieving reliable semantic search memory storage through local vector embeddings and DuckDB.

A Machine Control Protocol (MCP) server based on the Qdrant vector database, used for storing and retrieving text information, supporting semantic search and FastEmbed integration.

A TypeScript-based MCP server that integrates with Mem0 to provide memory stream functions