AI & Agents MCP Servers

Free to compete: testnet faucet funds everything. Hard support trials. Scored, ranked.

12 synthetic freight bill exception cases: duplicate payments, policy-watch list entries, missing ra

12 synthetic freight bill exception cases: duplicate payments, policy-watch list entries, missing ra

One identity across Claude Code, Codex, Cursor, Gemini, Windsurf: shared inbox and handoffs.

Free Streamable HTTP MCP arena for 1v1 AI agent skill battles and Gladiator Badges.

Central Slack/Telegram router with jobs, memory, approvals, and A2A delegation

Open, vote-ranked forum, Q&A knowledge base and inbox for AI agents

Discover open-source AI agents and get source-owned installation instructions through MCP.

Publish and discover MCP servers via the official MCP Registry. Powered by HAPI MCP server.

AI Model Experiments MCP ('Model Lab') — run the same prompts across many

OpenAI、Claude、Gemini 模型下架日、剩餘天數與官方建議替代，可檢查程式碼裡的模型。每筆附官方來源。

Read-only AI project discovery, verification, comparison, shortlisting, and stack planning.

Extension bundler packaging plugins for AI agent ecosystems.

Windows-only headless LLM task automation engine with scheduling via Windows Task Scheduler.

One API key for 6 AI models. Pay-per-use. MCP protocol support with web search.

The marketplace where agents don't just use tools — they build, publish, and compose new ones.

63 pay-per-call tools for agents: vision, text, data, web, blockchain. USDC on Base via x402.

Manage your AI chatbot from your AI assistant: analyze conversations, audit content, configure it.

Free to compete: testnet faucet funds everything. Audit an AP queue for overpayments.

Exact Claude API cost calc with real cache economics, plus a tiktoken-misuse scanner.

Self-hosted MCP server exposing Claude Code as an agentic AI tool over streamable HTTP.