"Allowing an AI agent to ask user questions during a task" matching MCP connectors:

290+ quality-scored API capabilities for AI agents across 27 countries via MCP.

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

SSRF-safe web intelligence: 4 outcomes, 43 paid x402 tools, 3 free tools and a URL preview.

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

Scores a business's online presence 0–100 and names the top issues to fix — search visibility, whether AI assistants can read and recommend it, speed and first impression, trust, and how easy the business is to reach. Give the scan_website tool a URL and it returns the score with the top issues, in chat. English and Arabic. By BottleTech (bottletech.net).

Live censorship, China economic, and tamper-evident AI evaluation tools with bounded analysis.

Fixter's MCP provides a stream-lined agentic way to onboard, setup and use the Fixter monitoring and observability platform. Check out more at https://fixter.dev/

AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence.

Audit MCP configs and skill files for over-broad scope and injection risk. 6 of 8 free.

Dead-man's-switch for cron jobs & AI agents. Import a crontab to arm one silent-miss alert per job.

Ask about your Dreambooth Studio photobooths: sessions, revenue, credits, projects, device status.

Inventory and audit your agent fleet over MCP: audit_mcp_config returns risk-ranked findings with a 0-100 posture score, scope_check ranks tool-manifest blast radius, audit_skill_file and injection_scan screen untrusted skill files and text, and inventory_report builds a governance inventory with risk tiers. All analysis is deterministic and local to the request.

AI news, model pricing, service status, and machine-payable premium tools. AFTA-certified.

Diagnose x402 seller endpoints: what is wrong with your 402 challenge, and how to fix it.

Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.

Usage metering + SLA accounting for agent services (the meter behind x402 micropayments).

Compute-is-carbon energy/carbon ledger for agent work with Landauer-limit validation.

CPU telemetry & benchmarking, SHA-256 hashing, AES-256-GCM storage, AI video/image via Nova.

Give AI coding agents access to your Vynix visual feedback, bug reports, and AI diagnosis.

Check if an MCP server tool changed or hides injection patterns before you trust it.