"Screen sharing or remote desktop access software" matching MCP connectors:

Pre-transaction token risk checks for autonomous agents. Read-only; never signs or moves funds. Paid per call in USDC via x402. Supporting Base, Solana, Ethereum, Arbitrum, BSC and HyperEVM

Evidence-gated task verification for AI agents. Decompose goals into acceptance criteria, attach proof (screenshot, curl, file), independent LLM judge accepts or rejects. 24 tools. Hosted remote MCP (streamable-http, OAuth 2.1 + DCR).

The PropelAuth Integration MCP Server helps you and your favorite AI agent integrate PropelAuth as quickly and easily as possible into your project. Whether you're integrating PropelAuth into your Next.js project or your FastAPI backend, the Integration MCP Server will ensure your AI agent has the best context possible for a successful integration.

Stop your agent before it runs rm -rf /etc or emails your .env. Deterministic preflight checks.

Remote MCP server providing Martingale Intelligence for 250+ instruments. Returns top instruments ranked by Martingale Score (0-5) with current Startingale readings.

Ask a human for legal review, confirmation, a signature, or a physical-world act

Deterministic next-step decisions after failed API, MCP, automation, or AI-agent actions.

Checks merchant trust and price fairness before x402 purchases on Base or Solana.

Locks, work queues and barriers for multi-agent work. Never reads your code, files or transcripts.

Buy 15 minutes of Alex Finger's time, or an AI Repellent certificate. Agents only.

Your saved nanoodle workflow graphs as MCP tools — BYOK or pay per call in Nano (x402)

Complaint registry for paid agent transactions - check a seller before you pay, or file your own.

Read-only Remote MCP for externally grounded AI agent trust receipts.

Paid work for agents: claim verifier-checked jobs, submit, earn USDC. Some need no bond or funding.

Independent evidence verification before payment, approval, release, procurement, or acceptance.

Self-destructing secret sharing for AI agents: encrypted burn links for credentials, plus an agent-to-agent dead-drop with exactly-once claim semantics. RAM-only, no database, open source (MIT). Source: https://github.com/mmmpym/flashpaper

X feedback discovery, noise-reduced query planning, signal filtering, and AI handoffs.

Get a real human to verify, decide, or improve an AI agent's work.

Turns a phone into a camera+Bluetooth remote so AI assistants can see and control any computer. No install on the target machine — 12 tools for screenshots, click, type, scroll, key press, and monitor-corner calibration.

Remote-first MCP adapter for emitting Settlement Attestation Receipts; not a verifier.