List documents and web pages ingested into a knowledge store for RAG retrieval, with pagination and filtering.
MIT
605,725 tools. Updated 2026-09-24 03:23
"RAG (Retrieval-Augmented Generation) system that can store papers and web pages" matching MCP tools:
- List all document stores with details for retrieval-augmented generation (RAG) in Flowise.MIT
- Ask questions about memory files using retrieval-augmented generation to get answers from stored content with configurable search modes.MIT
- Create a named local vector index for retrieval-augmented generation. Documents added are embedded via Ollama for local RAG without cloud dependencies.-
- Retrieve relevance-ranked web content—text chunks, tables, code blocks—for grounding AI answers, fact-checking, and RAG pipelines.MIT
- Scrape a public URL to create a searchable knowledge base. Extracts content from web pages (including JavaScript-rendered), chunks it, and indexes for RAG.MIT
Matching MCP Servers
- AlicenseBqualityDmaintenanceEnhances AI model capabilities with structured, retrieval-augmented thinking processes that enable dynamic thought chains, parallel exploration paths, and recursive refinement cycles for improved reasoning.124MIT
- 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.1Apache 2.0
Matching MCP Connectors
send-that-email MCP — wraps StupidAPIs (keyless — no credential needed)
tldr-pages community simplified man pages (cached 24h)
- Create a searchable knowledge base from plain text, automatically chunked and indexed for RAG retrieval. Ideal for FAQs, product specs, and policies.MIT
- List existing knowledge bases (documents, FAQs, web content) to prevent duplicates and find knowledge_base_ids for agent attachment.MIT
- Convert any public web page into token-efficient Markdown for RAG and AI agents. Optionally render JavaScript for single-page apps.MIT
- Perform semantic search over a stored memory namespace to retrieve the most relevant entries. Use this to recall context for RAG pipelines.MIT
- Confirm that the dryad-rag-pipeline service is reachable to ensure agents can reliably index and search documents.MIT
- Add knowledge entries to a RAG system to store insights, tips, and best practices. Categorize and tag them for efficient retrieval.MIT
- Store typed knowledge (observation, decision, learning, error, pattern) with tags, importance, and optional relation. Embeddings enable semantic retrieval.MIT
- Fetch any public web page and extract its readable content as clean markdown. Respects robots.txt, handles redirects, ideal for research and RAG.MIT
- Convert text into 4096-dimension vectors for retrieval-augmented generation or semantic search. Returns a summary of item count, dimensions, and input tokens so you can populate a vector store efficiently.MIT
- Store a dialog turn with role, content, and metadata to persistent session memory for later retrieval and context assembly.MIT
- Create a knowledge store to store documents for RAG, enabling AI agents to search and answer questions. Set dryRun=false to create.MIT
- Scan document collections, training examples, or RAG retrieval sets to uncover semantic anomalies and poisoned clusters using local embeddings and Isolation Forest.MIT
- Convert web pages to clean markdown format by extracting content, removing unnecessary elements, and ranking information for RAG applications.MIT
- Convert any permitted public web page into clean Markdown for AI agents or note-taking. Returns explicit errors for blocked, paywalled, or login-gated pages.MIT
- Given a URL, extracts the page title, readable markdown, and plain text. Helps AI agents read web content, scrape data, and feed RAG pipelines.MIT