Directory

Search MCP Servers

Explore 23,068 servers by name, category, or capability

Showing 1–24 of 70 for LLM RAG

Docs RAG

Enables AI to query and analyze local documents and Git repositories through a RAG system built with TypeScript, LlamaIndex, and Gemini embeddings.

Inkeep

Enables Claude to search and retrieve relevant documentation through Inkeep's RAG API, returning structured citation data for technical support and…

Shared Knowledge RAG

Enables AI systems to access and retrieve information from multiple vector store backends including HNSWLib and Weaviate, providing a unified interface for…

ArcKnowledge (Custom RAG)

Bridges AI systems to custom knowledge base APIs for retrieval-augmented generation across multiple text and image sources with configurable authentication and…

Minima

Search and retrieve context from local files for RAG.

LlamaIndex Documentation

Provides a RAG-powered query interface to LlamaIndex documentation, delivering detailed responses with code examples using LlamaCloud's managed index service

HR Policy Chatbot

Enables HR departments to provide workplace policy information through a RAG-based chatbot that indexes, retrieves, and generates answers from PDF…

GroundX RAG

Integrates with GroundX to provide document search and ingestion capabilities, enabling domain-specific knowledge retrieval without requiring direct access to…

AWS Knowledge Base

Integrates with AWS Knowledge Bases to retrieve information using Bedrock Agent Runtime, enabling RAG operations with structured metadata for organizational…

brandguide/AI MCP

Agents are taking over execution. When they write copy, generate visuals, or adapt messaging, they need structured brand knowledge — not PDFs and guesswork…

Qdrant Docs Rag

Retrieve and process documentation using vector search to provide context for AI assistants.

PDF Search

Built for Zed to enable semantic searching of PDF documents using a Qdrant vector database and OpenAI embeddings.

LLM Gateway

Unified gateway for managing multiple LLM providers with automatic model selection, semantic caching, and cost optimization features for reliable production…

Multi-LLM Cross-Check

Provides a unified interface for querying multiple LLM providers simultaneously, enabling side-by-side response comparison for fact-checking, gathering diverse…

Arize Phoenix

Provides a unified interface to Arize Phoenix's capabilities for managing prompts, exploring datasets, and running experiments across different LLM providers

whatsapp-mcp

Provides a secure bridge to your WhatsApp account, enabling message search, contact management, and sending capabilities while keeping all data stored locally…

WolframAlpha LLM

Integrates with WolframAlpha's LLM API to enable complex mathematical and scientific queries, offering tools for asking questions and getting simplified…

Code Review

Enables automated code reviews through multiple LLM providers by analyzing repository structures and evaluating code for security, performance, quality, and…

Mcpal

Lightweight MCP server for native desktop notifications with action buttons, text replies, and LLM-aware icons.

Mem0 (Long-Term Memory)

Provides persistent long-term memory capabilities through semantic indexing, retrieval, and search functions with support for multiple LLM providers and…

LM Studio

Bridges Claude with locally running LLM models via LM Studio, enabling users to leverage private models through Claude's interface while maintaining local…