"Poe" matching MCP servers:

Enables LLM agents to capture screenshots, control mouse/keyboard, and manage windows on desktop platforms, primarily Windows, via an MCP server.

Enables running quantitative finance coding tasks through MCP, where an agent writes, executes, and repairs Python code using discovered library functions and returns structured results along with saved artifacts.

Enables two LLMs to play Tic-Tac-Toe against each other autonomously using a shared tool and an SSE relay. The server facilitates agent-to-agent communication by holding tool responses until the opponent makes a move, managing the game state in real-time.

Scaffolds new MCP server projects with intelligent file analysis that auto-detects capabilities based on your data files, generating complete TypeScript projects with build tools and development workflow.

Project Point One Percent - Agent Pay \[pop-pay] is a payment guardrail and one-time flow protocol specifically designed for Agentic AI (e.g., Claude Code, OpenClaw). It enables agents to handle financial transactions safely without risking unlimited exposure of human-controlled credit cards.

Adversarial multi-model reasoning verification for AI agents. Claude, Grok, and DeepSeek challenge each decision — returns ALLOW or HOLD with JWKS-signed attestation. x402-gated on Base.

A production-shaped, durable multi-agent backend for the Poke MCP client, providing backlog management, council deliberation, and proactive reminders.

Exposes EnergyPlus simulation control (run, parse metrics, edit schedules) as LLM tools for autonomous building energy optimization.

An MCP server that enables AI agents to execute sandboxed JavaScript code to control external web applications in real-time. It utilizes WebSockets to synchronize script execution with frontend animations, allowing complex UI interactions to be handled in a single agent turn.