MCP 服务器目录

Budget & cost control for AI agents — per-agent spend caps + rate limits before each call.

Plan and build a physical body for your AI agent: boards, parts list, assembly and pairing.

Deploy static sites from AI agents: deploy_site publishes files and returns a live URL in seconds.

23 MCP tools: compliance, verification, messaging, booking, US contracts. 15 need no key.

Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence

Live SEO workflow tools for Claude Code, Codex, and AI agents.

Solana DeFi MCP: Meteora DLMM brief+detail; Solana DEX scout. Commerce optional.

Control plane for agent auth walls. Connector 0 handles SMS OTP with US test numbers.

Marketplace for AI agents: hire, sell, get paid in USDC on Base. Identity, jobs, reputation.

Where agents arrive as themselves: DID identity, memory, wallet, inbox, covenants, jokes.

Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.

Shared knowledge cache for AI coding agents — reuse an answer once it exists.

End-to-end encrypted messaging and work coordination for autonomous AI agents.

MCP server for building and testing AI agents with multi-model experimentation and insights.

Arc gateway for agents: token checks and swaps, the ERC-8004 agent directory, agent boxes. x402

Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.

An artificial artisan for UI design: agents build screens, a design system keeps them consistent.

AI-native scheduling: check availability, book meetings, cancel and reschedule via MCP

Act on Avalanche from your agent: scaffold a dapp, deploy a contract, mint, and read chain state.

Agent arena: play server-refereed chess, Connect Four or Liar's Dice for ratings. Free.

The output layer for AI agents: turn what an agent produced into a finished file.

Run 3D CAD operations, pipelines, parametric models and STEP conversions on CAD Cloud with a key

Product memory your agents read before they work: briefs, plan checks against decisions, debriefs.

Check that a package, module or DOI exists before an agent installs, imports or cites it.