"Amazon Web Services" matching MCP connectors:

Zero-Ops deploy of a private AI coding workspace onto your own VPS — straight from your AI chat. Provide only your Ubuntu server credentials and Fractera automatically configures everything (Nginx, HTTPS, auth, database, services) in about 10 minutes: 5 AI coding engines, an autonomous Hermes orchestrator, and private graph memory (LightRAG). No terminal, no DevOps. IP-first and free; a custom domain with HTTPS is an optional later step.

**ColdState Knowledge Search MCP Server** https://github.com/daniel-coldstate/coldstate-mcp Semantic search over 64.6M knowledge entries — the structured alternative to web search APIs and web scraping for LLM agents. No crawling, no rate limits, sub-3s responses. Cloud-hosted at services.coldstate.ai

Give your agent web search and authoritative datasets: S&P Global, FRED, OECD, SimilarWeb & more.

Brand health & trend footprint across PSFK expert graphs with citable sources, not web summaries.

Forensic archive of javaBin & JavaZone origins (1998-2007) as a signed KCP knowledge web.

Thor Henning Hetland's signed knowledge web: plan, load and verify ed25519-signed KCP units.

Norwegian open-source community wiki (2,290 articles, 2008-2022) as a signed KCP knowledge web.

Diffbot MCP — Knowledge Graph company enrichment + web content extraction (diffbot.com)

Knowledge Base von designare.at – Michael Kanda, Web & KI aus Wien. Semantische Suche über RAG.

Agent Module provides structured, validated knowledge bases engineered for autonomous agent consumption at runtime. Agents retrieve deterministic knowledge instead of scanning unstructured web content — eliminating hallucinated citations in regulated domains.

Simple, user-controlled memory for AI: keep, recall, update, and forget information across sessions. Designed for safety and clarity, it exposes only four explicit tools with no hidden behavior, giving agents reliable memory without complexity.

Full-control memory API for AI agents with direct access to structured data, relationships, and revision history. Built for advanced workflows, it enables precise querying, linking, and maintenance of a complete memory graph with full transparency and control.

Claim-level provenance preflight for sanitized nonfiction passages; automated triage only.

Universal memory for AI agents and tools. Save, organize and search context anywhere.

One MCP server, 13 agent services: hallucination firewall, context compression, cross-agent memory, token routing (11 providers), audit log. Free tier. Pay-per-use.

Search and get recommendations from your own saved catalog of developer tools and services.

Remote knowledge base built for teams. Bundled skill induces agents to autonomously record investigations, decisions, and recipes as bite-sized interconnected posts. Forum-style web UI for humans to browse the same graph. Compounds into a dense map of a team's tribal knowledge over time.

MCP memory server with shared team workspaces, typed knowledge chunks (decision, finding, convention, state, question, reference), role-based access, and cross-tool support for Claude, Cursor, and Codex. The only MCP memory server built for engineering teams. Features automatic deduplication, two-layer retrieval (LLM KB selection + hybrid vector/BM25/RRF fusion), a web dashboard with knowledge graph visualization, and attribution tracking. Zero server-side LLM costs.

Voice-led, FSRS-scheduled flashcards from YouTube, PDFs, web, or text. Auto-graded quizzes.

Simple memory for AI: keep, recall, update, and forget information across sessions.