MCPs tagged with # Retrieval-Augmented Generation

Driflyte MCP Server acts as a bridge between AI-powered assistants and diverse, topic-aware content sources by exposing a Model Context Protocol (MCP) server. It enables retrieval-augmented generation workflows by crawling, indexing, and serving topic-specific documents from web pages and GitHub repositories. The system is extensible, with planned support for additional knowledge sources, and is designed for easy integration with popular AI tools such as ChatGPT, Claude, and VS Code.

• ⭐ 9
• MCP
• serkan-ozal/driflyte-mcp-server

mcp-local-rag is a local server implementing the Model Context Protocol (MCP) to provide retrieval-augmented generation (RAG) capabilities. It performs live web search, extracts relevant context using Google's MediaPipe Text Embedder, and supplies the information to large language models (LLMs) for enhanced, up-to-date responses. The tool is designed for easy local deployment, requiring no external APIs, and is compatible with multiple MCP clients. Security audits are available, and integration is demonstrated across several LLM platforms.

• ⭐ 89
• MCP
• nkapila6/mcp-local-rag

Trieve offers a platform for semantic search, recommendations, and retrieval-augmented generation (RAG). It supports dense vector search, typo-tolerant neural search, sub-sentence highlighting, and integrates with a variety of embedding models. Trieve can be self-hosted and features APIs for context management with LLMs, including Bring Your Own Model and managed RAG endpoints. Full documentation and SDKs are available for streamlined integration.

• ⭐ 2,555
• MCP
• devflowinc/trieve

Implements a Model Context Protocol (MCP) server designed for integration with LLMs and Retrieval-Augmented Generation (RAG) pipelines, providing automated web search and web page extraction capabilities. Runs locally and interacts with the RAG Web Browser Actor in Standby mode, responding to queries by fetching, scraping, and returning cleaned content from the web as Markdown. Supports Google Search queries and direct URL fetching through a standardized 'search' tool interface, offering multiple output formats and programmable arguments. Deprecated in favor of mcp.apify.com but illustrates MCP server use for local web browsing integrations.

• ⭐ 194
• MCP
• apify/mcp-server-rag-web-browser

Vectara MCP Server implements the open Model Context Protocol to enable AI systems and agentic applications to connect securely with Vectara's Trusted RAG platform. It supports multiple transport modes, including secure HTTP, Server-Sent Events (SSE), and local STDIO for development. The server provides fast, reliable retrieval-augmented generation (RAG) operations with built-in authentication, rate limiting, and optional CORS configuration. Integration is compatible with Claude Desktop and any other MCP client.

• ⭐ 25
• MCP
• vectara/vectara-mcp

Biel.ai MCP Server enables AI tools such as Cursor, VS Code, and Claude Desktop to access and utilize a company’s product documentation and knowledge base through the Model Context Protocol. It provides a hosted RAG layer that makes documentation searchable and usable, supporting real-time, context-rich completion and answers for developers. The server can be used as a hosted solution or self-hosted locally or via Docker for advanced customization.

• ⭐ 2
• MCP
• TechDocsStudio/biel-mcp

Graphlit MCP Server provides a Model Context Protocol interface, enabling seamless integration between MCP clients and the Graphlit platform. It supports ingestion from a wide array of sources such as Slack, Discord, Google Drive, email, Jira, and GitHub, turning them into a searchable, RAG-ready knowledge base. Built-in tools allow for document, media extraction, web crawling, and web search, as well as advanced retrieval and publishing functionalities. The server facilitates easy configuration, sophisticated data operations, and automated notifications for diverse workflows.

• ⭐ 369
• MCP
• graphlit/graphlit-mcp-server

ApeRAG is a production-ready Retrieval-Augmented Generation (RAG) platform that integrates graph-based, vector, and full-text search capabilities. It enables the construction of knowledge graphs and supports MCP (Model Context Protocol), allowing AI assistants direct interaction with knowledge bases. Features include advanced document parsing, multimodal processing, intelligent agent workflows, and enterprise management tools. Deployment is streamlined via Docker and Kubernetes, with extensive support for customization and scalability.

• ⭐ 920
• MCP
• apecloud/ApeRAG

Agentset MCP provides a Model Context Protocol (MCP) server designed to power context-aware, document-based applications using Retrieval-Augmented Generation. It enables developers to rapidly integrate intelligent context retrieval into their workflows and supports integration with AI platforms such as Claude. The server is easily installable via major JavaScript package managers and supports environment configuration for namespaces, tenant IDs, and tool descriptions.

• ⭐ 22
• MCP
• agentset-ai/mcp-server

Provides an MCP server that brings Snowflake Cortex AI, object management, and SQL orchestration to the MCP ecosystem. Enables Cortex Search, Analyst, and Agent services for structured and unstructured data querying, along with automated SQL execution and object management. Designed for integration with MCP clients to streamline AI-powered data workflows and context-sensitive operations within Snowflake environments.

• ⭐ 176
• MCP
• Snowflake-Labs/mcp

Alibaba Cloud Tablestore MCP Servers provides multiple implementations (Java and Python) of MCP (Model Context Protocol) server-side components. It includes sample projects and a production-ready RAG-based knowledge Q&A system, enabling management of context and knowledge for AI applications on Tablestore. The libraries showcase standardized approaches for integrating Tablestore with modern AI use cases requiring context handling.

• ⭐ 148
• MCP
• aliyun/alibabacloud-tablestore-mcp-server