"How to scrape data from websites into JSON" matching MCP connectors:

MarkupBase turns AI-generated Markdown and HTML into durable, versioned artifacts that people can review and discuss. Its MCP server lets agents publish new versions, preserve contextual comments, include hosted images, and respond to feedback through secure account-linked identities, creating a clear human review boundary without requiring real-time editing.

Hosted MCP memory: save sessions/decisions once, search from Claude, Cursor, ChatGPT. EU-hosted FTS.

For queries a model can't confidently place: resolves or declines. Built to decline, not guess.

A semantic search server that gives AI assistants instant access to Dodo Payments documentation and knowledge base.

MCP server for German & EU law. Verified, citable legal context for any LLM. Daily updates from official sources, hosted in Germany

**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

Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.

Collaborative, cache-first web search for agents — cited answers from a shared live-web pool.

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

Create your digital twin: a public page that answers from your own material, with citations.

The first low-latency wire service purpose-built for AI agents. Ingests 54+ public APIs and 71k RSS feeds across 232 countries, outputs CWF (Cognitive Wire Format) – 80% shorter than JSON, sub-second WebSocket delivery. 9 MCP tools: get_latest_signals, search_signals, get_fused_signal, scope_signals, get_facet_manifest, list_facets, get_related_signals, list_data_sources, get_billing_profile. 26 citable fusion products with verifiable formulas – no black-box scores.

LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.

Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.

Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.

1 Google Search endpoints. Pay per call in USDC via x402.

Extract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats.

Parse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges.

Historical market memory for AI agents using semantic vector search across years of financial market data. Discover similar market regimes, price patterns, and market context for quantitative research and algorithmic trading.

Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.

Deterministic fact verification for AI agents — checksums & curated data, not guesses.