"A guide to finding data in public databases" matching MCP connectors:

Entity resolution — data mapping, SDK code generation, docs search, and error troubleshooting

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.

AI-powered data integration platform. Onboard users and run DPF data workflows.

Hosted MCP server for data analysis: CSV profiling, A/B tests, cohorts, funnels, trend forecasts.

Paste-your-data analytics over MCP, computed in code: csv_profile profiles columns and data quality, ab_test runs two-proportion z-tests, correlation and growth_rates cover the basics, with funnel_report, cohort_retention, and forecast_trend in the premium tier. No uploads, no external calls, no data retention.

Convert PDF bank statements to checked Excel, CSV or JSON with balance validation.

Find novel, statistically validated patterns in tabular data — hypothesis-free.

Converts customer-supplied PDF bank statements into checked Excel, CSV, or JSON with balance validation. Hosted Streamable HTTP endpoint; each user brings their own MainBook API key, and the server never connects to bank accounts.

Company-specific regulatory assessments for concrete business questions, as structured data or PDF.

Messy spreadsheets in, clean checkable tables out. Every result carries its arithmetic proof.

Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.

Auto-discover validation rules from data — scan, profile, health-score. No rules to write.

Post-scrape data cleaner, no LLM: repairs mojibake, HTML, invisible chars. Plus a verdict.

Pre-computed market data that improves agent reasoning, reduces token usage, and replaces pipelines.

DePIN telemetry, DAG manifold correlation, and verifiable data products for AI agents.

Find duplicate records in 30 seconds. Zero-config entity resolution, 97.2% F1 out of the box.

Multi-tenant FastMCP server for Charles Schwab brokerage data, monetized via DPYC Tollbooth

Buy timestamped web, company, commerce, social, document and decision data via x402.

Bounded data, document, web-quality, and operations services purchased with USDC through x402.

Scrapingdog MCP — wraps Scrapingdog (scrapingdog.com), a proxy-based web