Check the current status of the RAG documentation index, including total chunks, configured sources, and last update times.
Apache 2.0
484,048 tools. Updated 2026-08-28 03:47
"Using RAG to Provide Documentation to LLMs" matching MCP tools:
- Get precise answers to any question about Lamatic.ai documentation by searching all indexed docs with RAG.MIT
- Extract the clean main content of any web page by rendering with real Chromium to handle JavaScript, then stripping ads and boilerplate. Returns Markdown, text, or HTML for use in LLMs and RAG.MIT
- Display session efficiency statistics: token usage, RAG savings, and patterns learned. Quantify context saved by RAG versus loading full documentation.MIT
- Displays session efficiency: token usage, RAG savings, and learned patterns. Call after multi-step tasks to reveal context saved by RAG versus full documentation loads.MIT
- Look up how to use any CrewAI feature, tool, or pattern by querying the internal documentation RAG engine. Returns relevant snippets with source URIs.MIT
Matching MCP Servers
- AlicenseAqualityCmaintenanceAI-powered MCP server for file renaming, organization, and PDF splitting using natural language prompts and content analysis.417MIT
- FlicenseNot gradedqualityBmaintenanceMCP server that converts PDF, video, web, and audio inputs into structured Markdown notes with support for checkpointing, batch processing, and Obsidian integration.
Matching MCP Connectors
Fetch URLs and return clean Markdown for RAG — nav, ads and boilerplate stripped.
Transform any blog post or article URL into ready-to-post social media content for Twitter/X threads, LinkedIn posts, Instagram captions, Facebook posts, and email newsletters. Pay-per-event: $0.07 for all 5 platforms, $0.03 for single platform.
- Search Maya API documentation using hybrid RAG to find relevant code examples, command flags, and solutions for maya.cmds, PyMEL, Arnold, and Maya-USD. Use before writing complex Maya commands to verify syntax and avoid errors.MIT
- Retrieves relevant passages from a long document or text using RAG, enabling targeted search without loading full content. Provide a query and a file path or text to get matching sections.MIT
- Estimate AI model costs by supplying token counts for LLMs or unit counts for media models, such as images or seconds.MIT
- Rerank retrieved passages by relevance to a query using NVIDIA NIM models. Improves RAG pipeline retrieval quality by reordering results with a reranking model.MIT
- Retrieves documentation from a specified GitHub repository to generate prompts for LLMs.Apache 2.0
- Search documentation for code examples matching your query. Get working examples for Griptape patterns like RAG pipelines, custom tools, or workflows.MIT
- Fetch Next.js documentation by path, using the documentation index to find the correct path.MIT
- Convert Sphinx documentation directories to Markdown optimized for LLMs, making technical content readily accessible to language models.MIT
- Update an existing documentation page. All fields are optional — only provide the fields you want to change.MIT
- Search a RAG vector store to find code relevant to a query. Optionally expand results using the project's call graph.MIT
- Search uploaded documents using RAG to find answers with citations. Ask questions to retrieve information from your knowledge base.MIT
- Download entire documentation websites for offline RAG indexing by providing a URL, enabling configurable depth and asset capture.MIT
- Get answers to questions by retrieving relevant information from wiki content using RAG technology.MIT
- Identify content coverage gaps by analyzing URLs against user queries using Query Decomposition and Self-RAG techniques to reveal missing information.Apache 2.0