Perform semantic search over a stored memory namespace to retrieve the most relevant entries. Use this to recall context for RAG pipelines.
MIT
626,502 tools. Updated 2026-10-01 11:29
"Information on Rag and Memory" matching MCP tools:
- Retrieve current connection status, latency, and version details for Memory Server, RAG Server, and Google services to verify service availability.MIT
- Verify RAG and Memory server availability, including collection and schema auto-creation status. Use detailed mode for protocol and latency details.MIT
- Retrieve system information including kernel version, architecture, hostname, uptime, and memory statistics. Works on any system; returns SUSE variant and architecture details.GPL 3.0
- Get answers to questions by retrieving relevant information from wiki content using RAG technology.MIT
- 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.-
Matching MCP Servers
- AlicenseAqualityBmaintenanceServes UltraRAG memory to agents over stdio MCP, providing project-local and per-user global memory. It lets agents read and append standing memory and daily dialogue rounds in UltraRAG's format, with an optional browser view.4Apache 2.0
- AlicenseAqualityBmaintenanceEnables persistent project memory for Hermes Agent by storing and retrieving wiki, code, and learning layers locally, with tools to recall, learn, retire, and ingest information beyond the context window.6MIT
Matching MCP Connectors
Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
Recall your team's coding-agent memory. Install the Assertion plugin to capture it automatically.
- Get answers to questions by retrieving relevant information from wiki content using RAG technology.-
- Retrieve host system details including operating system, CPU, memory, user, and active workspace for environment inspection.MIT
- Convert text into a numeric vector for semantic search, RAG, and similarity. Supports multiple languages.MIT
- Check the current status of the RAG documentation index, including total chunks, configured sources, and last update times.Apache 2.0
- Retrieve server health information including version, uptime, memory usage, cache statistics, and Node.js version.MIT
- Compress raw HTML into clean markdown and headings to fit more within RAG context windows.MIT
- Update an existing memory to fix incorrect information after searching. Changes content, project, or memory type and re-computes the embedding.-
- Scrape and index up to 20 URLs to add their content to the RAG corpus, providing source material for content marketing ideas.MIT
- Search the RAG corpus with semantic and keyword hybrid search to find relevant content marketing ideas.MIT
- Confirm that the dryad-rag-pipeline service is reachable to ensure agents can reliably index and search documents.MIT
- Remove stored information from persistent memory by specifying its unique identifier to maintain accurate long-term context.MIT
- Retrieve detailed information and evidence for a specific memory entry by providing the repository and memory ID.MIT
- Store facts, notes, or information in shared memory. Automatically classifies, checks conflicts, and builds a knowledge graph.MIT
- Add knowledge entries to a RAG system to store insights, tips, and best practices. Categorize and tag them for efficient retrieval.MIT
- Execute a complete RAG workflow: generate query embeddings, search document chunks, and return a direct answer grounded only in the retrieved context.MIT