"Alibaba.com" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceBuild and edit real websites from ChatGPT, Claude or Cursor in Swebsy's visual editor. Sign in with a free Swebsy account and your agent adds sections, edits text and styles, and manages pages in your open Swebsy Studio tab, where you see every change and can tweak it by hand. Export static HTML/CSS/JS or publish one site free. No install, no per-token fees.
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Now part of GAIP Diagnose: diagnoses failed agent or API calls (gaip_diagnose).
Spin up a complete OpenCode development environment on any Linux box — one agent-driven workflow, six tools, zero secrets.
Find your next useful task, share your capabilities, and collaborate directly with other agents on TaskBounty. Start: https://www.task-bounty.com/board/start?utm_source=glama . The focused Agent Board endpoint https://www.task-bounty.com/api/mcp/board exposes 14 tools without signup or API key: find_next_board_action, introductions, discussions, swarm claims, evidence, review, and return-to-work inboxes. Swarm tasks are unpaid collaboration; paid marketplace opportunities are separate, require confirmed funding and terms, and may be unavailable. This full MCP server also supports marketplace hiring and JavaScript/TypeScript sandbox-verified workflows; private account tools require a TaskBounty API key. Stay within operator authorization. Swarm acceptance is not sandbox verification or payment.
Collide is an MCP layer that keeps concurrent AI agents from stepping on each other in a shared codebase. It tracks code at the symbol level with a Merkle tree, so agents declare intent before writing, get warned about collisions, and pick up context on what changed and why. It also carries anchored team memory, merge simulation, and an audit ledger.
Push Realm is an MCP server and AI agent knowledge network where agents search proven fixes, publish what worked, and turn dead ends into open problems other agents can close. Compare how agents and tools perform in different topic areas.
Finds real, maintained open-source repos that fit your project. MCP grounding for coding agents.
Build and publish full-stack web and mobile apps on Floot from any MCP client. Building is free.
Tested, version-pinned code recipes for AI coding agents, each with its last-passed receipt.
AI app builder and APK maker for Android. Create and edit apps without coding.
Signs up to your live app like a new person and shows what breaks. Every app gets one free check.
Change-aware CI validation and affected-test guidance for coding agents.
Design a React Native app in a browser and emit it as a real Expo project you own, iOS and Android.
x402-gated safety checker for npm and PyPI packages. Built for AI coding agents to call before running npm install or pip install — flags nonexistent/typosquatted names, known CVEs (OSV.dev), and suspiciously new or low-download packages. $0.005 USDC per check on Base mainnet
Authenticated async Sonnet 5 Agent agent with status polling and artifact results.
Build real websites and web apps with AI, right from your chat. Describe your idea and WebTwizz builds it: landing pages, online stores, booking sites, portfolios and full web apps with sign-ins and a database. Change anything by asking, publish to a free webtwizz.app address or your own domain, undo changes, edit your site's database records, and sync the code with GitHub. Sign in with a free WebTwizz account (OAuth).
Coding agents in one repo see each other, get warned before shared edits, and message.
One place for every AI agent's pages and docs: versioned links to share, search and update.
Description: ▎ Spec-driven AI development workflow tools for Claude Code. Manage PRD → Design → Impl → Agent Task lifecycles, search and execute AI Prompts, and ▎ track traceable software delivery — all from Cl
