QBT Labs

#MCP #AIAgents #Crypto #Trading #OpenSource #x402

OpenMM Skills Hub is live 🔔 Multi-exchange trading tools, now agent-native. Your AI can now: ✅ Check real-time prices, spreads & orderbooks ✅ Run grid strategies ✅ Access Cardano DEX pools ✅ Manage portfolio across exchanges ✅ Trade across MEXC, Gate, Kraken, Bitget Works with Claude Desktop, Cursor, Claude Code, and OpenClaw. As the agentic economy grows, the context provided to AI systems becomes just as important as the code itself. 🔜 Next week: x402 integration Explore -> agents.openmm.io

@Indigo_protocol 🙌🙌

1,700+ downloads across Indigo + Cardano MCP packages in the last 14 days. Developers are already integrating: • Loans & leverage • Stability Pools • Order book executions • DEX routing AI-native DeFi is here. ⚡️

The next generation of traders won't have a bedtime. OpenMM is now ready. Two integration paths, one API, one CLI. MCP server. Skills. Openclaw plugins. 🔌 MCP Server: github.com/QBT-Labs/openm… 🧠 Agent Skills & Plugins: github.com/QBT-Labs/OpenM…

OpenMM now has complete documentation: 🤖 agents.openmm.io → AI Skills/Plugins, MCP setup, prompts library 📖 docs.openmm.io → Quick start, CLI reference, strategy guides 🔌 api.openmm.io → 18 REST endpoints, schemas, try-it-out Start here: docs.openmm.io/getting-starte…

Exchanges are racing to ship MCPs. We built the bridge that connects them all. OpenMM connects your AI agent to all of them: • Kraken • Gate • Bitget • MEXC • All Cardano DEXs And many more upcoming integrations. One SDK. One MCP server. Many different skills. One interface. Your agent doesn't need to learn 10 different APIs. It just talks to OpenMM. agents.openmm.io

OpenMM setup just went from "read the docs" to "answer 3 questions" npx @qbtlabs/openmm-mcp setup Pick your MCP client → pick your exchanges → paste API keys → done. Your AI agent is now a trader. Ask it: "What's my MEXC balance?" "Place a limit buy for 100 ADA at $0.35" "Start a grid strategy on BTC/USDT" Works with @AnthropicAI , Cursor, @windsurf and @openclaw Ship it 🚀

Part 2 of Market Making Decoded drops tomorrow. This one covers the actual mechanics — how we calculate spreads, manage inventory, and why depth matters more than the number at the top of the book. What would you want to know about how spreads are set?

@0xsamt Every platform is shipping AI agent infra. We built the market making layer for the same stack. OpenMM MCP → 13 trading tools Agent Skills → grid trading, portfolio tracking Works with Claude, Cursor, OpenClaw github.com/QBT-Labs/OpenM…

> BNBchain highlighting community-builtAI agent skills > OKX launching OnchainOS with AI agent support with trading, market data, MCP and Skills, built in > Moonpay launches MoonPay Agents for autonomous transactions with multi-chain and native x402 support Crypto x AI synergies are here - one of the most interesting emerging sectors

@BNBCHAIN @Unibase_AI Same x402 infrastructure, for a different layer. We built OpenMM for AI agents that need to actually trade — not just transfer. 13 MCP tools • Grid strategies • Multi-exchange x402 for payments. OpenMM for trading. github.com/QBT-Labs/OpenM…

More options for seamless x402 micropayments on BNB Chain as @Unibase_AI expands support for gasless ERC-20 transfers! Note: This post is for informational purposes only and not financial advice. DYOR. x.com/Unibase_AI/sta…

@systematicls Interesting read sir 👌

@krypto_hybrid Thank you, appreciate it 🙏

@QBTLabs I'm super bullish on you Legend @QBTLabs Would love to connect and create with you 🧘‍♀️❤️

The ecosystem is converging. BNB Chain gives agents on-chain skills via MCP. We built the same architecture for market making: - OpenMM - MCP Server → 13 trading tools for Claude, Cursor & any MCP client OpenMM - Agent Skills → grid trading, order management, portfolio tracking across 20+ platforms Same standard. Same platforms. Different layers of the stack. Together this means an AI agent can read on-chain data AND execute trades — natively. github.com/QBT-Labs/OpenM…

Building AI agents on BNB Chain? 🤖 You can now equip your agent with skills to access BNB Chain with MCP tools: • Read chain data and smart contracts • Execute transactions and manage wallets • Register onchain agent identities (ERC-8004) Works across Cursor, Claude Desktop, OpenClaw and more. Start with this prompt 👇 “Read docs.bnbchain.org/showcase/mcp/s… and learn the skill to connect to bnbchain using the mcp”

This is huge for AI trading agents. We built the repo OpenMM-ai — open-source market making skills that already work natively with @OpenClaw via MCP and 20+ different platforms. Market Making, different strategies, multi-exchange execution across @Gate @krakenfx @bitget @MEXC_Official — all as Agent Skills, installable in one line. Now with @cryptocom in the mix, the infra is getting real. Read more here -> github.com/QBT-Labs/OpenM…

🦞 OpenClaw API integration is live in the Crypto.com App! You can now generate an API key using the Agent Key feature and deploy your AI trading agent: 🚧 Set a Budget: Control your agent’s weekly trading limit 🛡️ Secure Access: Choose exactly what the AI sees and does 🤖 Total Control: Approve every trade via chat or stop them all instantly Learn more 👉 crypto.com/en/product-new…

Exactly. We learned this building OpenMM — if the agent can't read the state properly, every action downstream is a guess. SDK gives you the primitives. MCP makes them accessible. Skills make them usable. x402 makes them sustainable. That's the path we're building for Indigo too. Skills are next in the architecture. Each layer has to earn trust before the next one works.

We designed this architecture with @Indigo_protocol and @3rdEyeLabs. The AI-native path for Indigo is: SDK → MCP → Skills → x402 Full AI agent compatibility. AI agents that can read Indigo data, execute transactions, and pay for DeFi access autonomously.

@ClawdateAI @openclaw @cursor_ai Who could imagine that some weeks ago 🦞

@QBTLabs @openclaw @cursor_ai love seeing more agent skills on OpenCLAW. we're building on it too but for a wildly different use case, 323 agents on clawdate so far just chatting each other up and finding compatible humans. the ecosystem is getting weird in the best way 🦞

We just open-sourced OpenMM-AI — agent skills for multi-exchange market making. 3 npm packages. 4 skills on ClawHub. 13 MCP tools. Works with @openclaw , @cursor_ai , Codex, Gemini CLI, and any MCP client. Here's what it looks like: - Type /balance mexc and get your exchange balances. - Type /price kraken ADA/EUR and get real-time prices. - Run grid strategies with /strategy. MEXC / Gateio / Kraken / Bitget supported. Cardano DEX integration built in. The OpenMM Ecosystem: → OpenMM-AI (Skills) — github.com/QBT-Labs/OpenM… → OpenMM (Core SDK) — github.com/3rd-Eye-Labs/O… → OpenMM-MCP (Tools) — github.com/QBT-Labs/OpenM… Packages: → @qbtlabs/openmm-trading → @qbtlabs/openmm-market-data → @qbtlabs/openclaw-openmm Everything is open-source. Install with npm, configure your API keys, and your AI agent can trade. Next: x402 payment integration to complete the stack. #OpenMM #AgentSkills #MCP #OpenClaw #Cardano #x402 #MarketMaking