Ask questions about memory files using retrieval-augmented generation to get answers from stored content with configurable search modes.

Generate text embeddings to enable semantic search and Retrieval-Augmented Generation (RAG) applications.

Upload files to process and index them for searchable knowledge retrieval using RAG (Retrieval-Augmented Generation) technology.

Search uploaded documents using RAG to find answers with citations. Ask questions to retrieve information from your knowledge base.

Delete files from the RAG system to manage storage and maintain relevant content for retrieval-augmented generation tasks.

Retrieve statistics about the Retrieval-Augmented Generation system's performance and usage metrics to monitor and analyze its operational data.

Retrieve detailed information about a specific RAG project within the Calibre ebook library, including its configuration, contents, and organization for semantic search and contextual conversations.

Add files to a RAG system for document retrieval, supporting PDF, DOCX, TXT, MD, CSV, and JSON formats to enable semantic search and information access.

Extract answers from web pages by analyzing content with AI. Provide a URL and question to get specific information from the page.

Parse code files into semantic chunks like functions and classes to improve RAG retrieval accuracy for research and analysis.

Query documents with context using a Retrieval-Augmented Generation (RAG) system. Automatically creates an index if it does not exist, enabling quick access to relevant information from stored repositories and text files.

Execute RAG queries against Amazon Bedrock Knowledge Bases to retrieve relevant documents using vector search for enhanced information retrieval.

Parse code files into semantic chunks like functions and classes to improve RAG retrieval accuracy for code analysis and documentation.

Clear the LAZY-RAG cache to remove outdated or incorrect data and start fresh for accurate information retrieval.

Retrieve details about a browser automation code generation session to track progress and access generated scripts.

Retrieve details about a code generation session by providing its session ID. This tool helps users access specific session information for efficient debugging and analysis.

Retrieve detailed information about a code generation session by providing its session ID using the Playwright-powered MCP server for browser automation.

Answer questions about enterprise knowledge bases using retrieval-augmented generation with context-aware responses and source citations.

Execute a complete Retrieval-Augmented Generation workflow to answer questions using document context. This tool automatically processes queries, generates embeddings, performs semantic search, and returns answers based strictly on retrieved content.

Execute complete RAG workflows to answer questions using document context. Handles embedding generation, semantic search, and context retrieval automatically for Teradata databases.

Create a knowledge base in Amazon Bedrock to store and organize documents for retrieval-augmented generation (RAG), supporting vector search, custom parsing, and chunking strategies.

Retrieve detailed information about an image generation session including metadata, assets with prompts and toolchains, and iteration history to review outputs and understand generation processes.

Ask questions using RAG-enhanced context from xAI Collections with LAZY-RAG cache for faster repeated queries.

Retrieve available RAG categories from MapRag to identify specialized retrieval servers for tasks requiring citations, freshness, privacy, or domain expertise.

Monitor LAZY-RAG cache performance by retrieving statistics including hits, misses, hit rate, and cache size to optimize retrieval efficiency.

Retrieve details about a specific code generation session using its session ID to access browser automation results and generated test code.

Retrieve details of a specific code generation session by providing its session ID, enabling tracking and management of automated test code creation within the Playwright MCP Server environment.

Generate Stylus/Rust smart contract code for Arbitrum using RAG context and version-aware generation. Supports ERC standards and custom contracts with optional tests.

Add documents to a RAG corpus for AI-powered search and retrieval within the AI Ops Hub, enabling secure access to local files, web pages, and notes for developer operational tasks.

Add books to a RAG project for vectorization and context search, enabling semantic search and retrieval from your Calibre ebook library.

Generate search results optimized for RAG context by providing relevant web content based on your query, with adjustable depth and result limits.

Embed and index documents into Chroma vector database for semantic search and retrieval-augmented generation workflows.

Get answers to questions by retrieving relevant information from wiki content using RAG technology.

Get answers to questions by retrieving relevant information from wiki content using RAG technology.

Search and filter RAG-capable MCP servers from the RAGMap registry to find the right retrieval tool based on categories, transport type, citations, and other constraints.

Retrieve details of a specific code generation session by its ID, enabling efficient tracking and management of browser automation tasks within the Playwright MCP Server.

Search Redis documentation to understand concepts like caching, session management, rate limiting, semantic search, RAG, and real-time analytics for AI applications.

Search project design documents, decisions, and specifications using semantic, keyword, or hybrid queries to find relevant artifacts for RAG scope exploration.

Retrieve video generation status and results from Sora tasks. Check if generation is pending, succeeded, or failed, and get video URLs with complete metadata.

Index files, directories, YouTube videos, or GitHub repositories into PinRAG's searchable database for retrieval-augmented generation with automatic format detection and batch processing.

Retrieve accurate answers and verify facts by leveraging Gemini 2.0 Flash and Google Search integration. Ideal for general knowledge queries, fact-checking, and detailed information retrieval.

Perform web searches to retrieve structured, source-cited data optimized for AI agents and RAG applications.

Execute search-augmented research queries routed to Perplexity for fact-checking, current events, and source verification. Delivers web-grounded answers for market research.

Retrieve detailed information about a specific ClickUp task using its ID or name. Use task ID for precise retrieval or task name with optional list name for identification.

Retrieve current generation queue details to monitor running and pending AI image processing tasks in ComfyUI.

Get information about the Netmex MCP server, including its purpose and capabilities for building custom AI assistant tools.

Retrieve detailed build and runtime information about the DollhouseMCP server to understand its configuration and operational status.

Retrieve details about records currently highlighted in DEVONthink to access document information without manual searching.

Retrieve detailed information about the current Figma document to understand its structure and contents for design analysis.

Retrieve information about the currently authenticated user in Linear to verify identity and access permissions for project management tasks.

Retrieve detailed information about an API specification from Postman using its unique identifier to access documentation, endpoints, and parameters.