"A platform for exploring AI-powered conversational tools" matching MCP connectors:

Curagent analyzes Florida real estate title documents — deeds, title commitments, mortgages, and full closing packages — and returns a structured risk report in seconds: composite score, itemized findings (liens, easements, probate gaps, boundary conflicts), and AI cure guidance. Built for title companies, lenders, and real estate attorneys who need to triage title risk fast without reading every page by hand. Currently Florida-only, with more states on the way. Request an API key at curagent.io.

DXF and PDF/X-4 for AI agents: structured facts, PNG renders, an interactive in-chat viewer.

500+ pay-per-call tools + skill packs. USDC + USDG on 12 chains, or free via proof-of-work.

Neutral freight reference + validation layer for AI agents: ADR, HS, UN/LOCODE, freight math

Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.

Live exit costs by venue, depth concentration, and a sealed calls record that keeps its misses.

Independent auditor for Japanese construction & renovation estimates; flags overcharge risk.

Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.

Live internet-censorship signals and tamper-evident, pre-registered, hash-chained AI model evals.

Reference data for prediction markets: graded resolution clarity, cross-venue links, provenance.

AMZScout Skill + MCP gives AI agents live access to real Amazon marketplace data across 14 Amazon marketplaces. Analyze any ASIN, validate product ideas, research niches, compare competitors, discover profitable keywords, and build data-driven PPC strategies using trusted Amazon insights instead of AI assumptions. Works with Claude, ChatGPT, Cursor, and any other MCP-compatible AI client. To connect, you'll need an AMZScout API plan and authorize your account. Get access and view pricing here: https://learn.amzscout.net/amazon-product-api-for-ai-agents

The Brain Layer for AI Trading Agents — quant calls + cross-venue arb across perp venues via MCP.

AI URL safety validator: SAFE/SUSPICIOUS/DANGEROUS verdict, trust score, threat intel.

Funding stress early warning for US money markets from free public data, with an honest backtest.

Agent-facing intake for HORIZON SHIELD, the Japanese construction estimate auditor.

Real-time tennis scores, players, odds and model win-probability for ATP, WTA, Challenger, ITF.

French & European company registry for AI agents: KYB, sanctions, annual accounts. x402, no API key.

AI-readable directory + commerce layer: 3,500+ SEA businesses, plus products from verified stores.

AgentFeed: 47 tools — our own liquidation tape + tokenized-equity peg data, paid in USDC.

Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.