Scrape a web page, embed the content, and store vectors in your vector database in a single call. Add web data to your RAG pipeline for retrieval.
MIT
298,713 tools. Last updated 2026-07-14 16:44
"A server/tool for RAG-based documentation scraping and retrieval with SSE support" matching MCP tools:
- Find relevant documentation pages from Apify Platform, Crawlee JavaScript, or Crawlee Python by using keyword-based full-text search. Returns URLs and content excerpts.MIT
- Scrape a web page, divide its content into structured text chunks optimized for RAG retrieval, and return them ready for downstream processing. No embedding or vector database required.MIT
- Get precise answers to any question about Lamatic.ai documentation by searching all indexed docs with RAG.MIT
- Create a searchable knowledge tool for retrieving documents. Integrates selected knowledge folders into a custom tool for RAG-based document search.MIT
- Parse code files into semantic chunks such as functions, classes, and methods to improve retrieval in RAG systems.MIT
Matching MCP Servers
- AlicenseBqualityDmaintenanceEnables retrieval-augmented generation by embedding queries with a chosen provider (e.g., OpenAI) and searching supported vector stores (Pinecone, pgvector) to return relevant content.Last updated1Apache 2.0
- Flicense-qualityCmaintenanceEnables AI coding assistants to query private academic paper collections via standard MCP tools, with hybrid retrieval, reranking, and inline citations.Last updated
Matching MCP Connectors
Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients
Generic URL crawl + HTML extraction — fallback for sites without dedicated MCPs.
- Ask questions enhanced by RAG context from xAI Collections, with cached responses for fast repeat queries.MIT
- Search and filter RAG-capable MCP servers by query, categories, score, transport, and other criteria to find the right retrieval server for your task.MIT
- Check real-time train ticket prices for routes in Spain. Uses web scraping to provide actual pricing with pagination support.MIT
- Exit the server with code 0 to trigger a process manager restart, loading updated code and tools after SSE reconnection.MIT
- Access support contact details, documentation URLs, API references, and GitHub issue reporting for Optimizely DXP deployment assistance.MIT
- Discover available tools from any MCP server by specifying its command or URL. Returns tool names, descriptions, and input schemas for integration planning.MIT
- Retrieve metadata for a live incident stream, including endpoint URL, payload schema, reconnect policy, and event-rate statistics, to prepare for SSE feed subscription.MIT
- Display session efficiency statistics: token usage, RAG savings, and patterns learned. Quantify context saved by RAG versus loading full documentation.MIT
- Open a browser-based terminal on a remote system via SSH to run interactive commands and scripts with full TTY support.MIT
- Create a new vector store to organize documents for semantic search and RAG. Attach files, set expiration, and configure chunking strategy.MIT
- Chunks documents at paragraph boundaries for RAG pipelines. Provides deterministic IDs, token counts, metadata, and overlap support—no LLM required.MIT
- Run faithfulness and retrieval quality evaluation over a batch of RAG pipeline cases, producing a summary report with mean metrics and worst-performing cases.MIT
- Retrieve documentation for the Harvest MCP server's time tracking tools, including general server information or specific tool details.MIT
- Extract structured data and text content from web pages using specific instructions and JSON schemas for scraping, information gathering, or content retrieval.Apache 2.0