Retrieve relevance-ranked web content with actual page text, tables, and code for AI grounding and RAG pipelines.
223,554 tools. Last updated 2026-06-22 02:07
"Rag llama" matching MCP tools:
- Find diverse nearest neighbors by balancing relevance and diversity, reducing redundant results. Ideal for RAG pipelines needing broad coverage.Apache 2.0
- Fetch detailed Actor information by ID or full name, including description, input schema, statistics, and pricing. Control returned fields via the 'output' parameter.MIT
- Filter documents by metadata before ranking by vector similarity to enable production RAG and semantic search pipelines.MIT
- Execute a complete RAG workflow to answer questions using retrieved context documents. Handles embedding, semantic search, and answer generation with direct quotes.MIT
- Check the indexing status and coverage of your PDF knowledge bases. View document and chunk counts, last build time, and un-indexed PDFs to ensure your RAG corpus is complete.AGPL 3.0
Matching MCP Servers
- AlicenseAqualityAmaintenance"primitive" RAG-like web search model context protocol server that runs locally. ✨ no APIs ✨Last updated5126PythonMIT
mcp-server-rag-web-browserofficial
Alicense-qualityFmaintenanceImplementation of an MCP server for the RAG Web Browser Actor. This Actor serves as a web browser for large language models (LLMs) and RAG pipelines, similar to a web search in ChatGPT.Last updated40204Apache 2.0
Matching MCP Connectors
Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients
Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
- Measures the fraction of retrieved RAG context chunks that are relevant to the question, providing a precision score to diagnose retriever noise and quality.Apache 2.0
- Generate vector embeddings from text for semantic search, RAG, clustering, or similarity tasks. Choose between query or document input type and adjust model quality and dimensionality.MIT
- Retrieve a list of all knowledge folders in your organization, each containing documents for RAG capabilities.MIT
- Query Vectara's RAG system to retrieve search results and generate contextual responses using specified corpus keys and API parameters for accurate information extraction.Apache 2.0
- Find relevant information from curated skills and documents using natural language queries. Semantic search leverages vector embeddings for more accurate results than keyword search.MIT
- Lists all available RAG categories indexed by RAGMap to help you identify suitable retrieval servers for your task.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
- Record retrieval queries, chunks, scores, sources, and rankings for later audit and diff workflows.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
- Preview what will be removed (chunks, images) from the RAG knowledge base, then confirm to delete the document and all associated data.MIT
- Clears the RAG cache to drop all cached retrievals, forcing the next query to rebuild from source. Use after context changes for fresh results.MIT
- Analyze git diff between two refs to map changed files to wiki pages and code entities, or answer questions about the diff using RAG.MIT
- Retrieve recent decisions from Clawket's RAG repository to review decisions made in previous sessions. Filter by project plan or creation timestamp. Returns a list sorted by newest first. Use for session context updates.MIT