"Construct 3" matching MCP servers:

基于MCP架构的微信公众号文章爬虫系统，支持AI智能体通过Selenium自动抓取微信公众号文章内容和图片，实现文章内容的智能分析。

ARGUS-3 stdio MCP server (argus_ask, argus_status). WARDEN vets third-party MCP servers before any tool runs.

An MCP server that enables web search capabilities using OpenAI's o3 model, allowing AI assistants to perform text-based web searches and return AI-powered results.

Agent marketplace with human concierge. Submit service requests in natural language, get quoted in sats, pay via Lightning Network. 3 MCP tools: submit_request, check_status, list_services.

Open source contribution manager — tracks PRs across repos, discovers contributable issues, diagnoses CI failures, and drafts maintainer responses. 21 MCP tools, 5 resources, 3 prompts. Ships as CLI, MCP server, and Claude Code plugin.

An AI personality collaboration tool based on Model Context Protocol (MCP) that enables users to summon and collaborate with multiple AI personas for intelligent analysis and problem-solving.

Runs a task through 3 parallel AI models (China or USA preset) and returns concise responses for Claude to synthesize.

A universal Model Context Protocol implementation that serves as a semantic layer between LLMs and 3D creative software, providing a standardized interface for interacting with various Digital Content Creation tools through a unified API.

A control plane for AI agents and human supervisors. Persistent task registry with scoped permissions, inter-agent delegation, and full provenance — all accessible via MCP. Deploy on Supabase free tier in 3 commands.

Enables autonomous agents to detect under-specified, high-stakes user goals, assess their reversibility and risk, and construct minimal multiple-choice clarifications before executing. Runs as a zero-dependency MCP server or importable Python module that gates autonomous execution behind those clarifying questions.

Enables any agent to spawn and manage T3 Code agent threads over HTTP MCP — starting research or coding agents, sending follow-ups, waiting for results, and answering approval prompts. It pairs once as a T3 device, exposes 15 tools, and keeps operations retry-safe.

Enables AI agents to manage Kanban boards, cards, sessions, and automations through a unified MCP interface with real-time updates, supporting delegation, agent sessions, and human-in-the-loop interactions.

MCP server that enables Claude Code to orchestrate multi-model AI consensus by querying GPT-5.2 and Gemini 3 Pro simultaneously, synthesizing high-confidence responses.

Enables MCP clients to call Cloudflare Workers-hosted tools while automatically tracking events, checkpoints, and tool calls in Agnost AI analytics.

Model Context Protocol server that standardizes tool discovery, execution, and context management for AI applications.

A ready-to-run MCP gateway and multi-agent scheduling system with 14 built-in tools and 3-layer performance optimization, reducing latency by 65%.

Enables AI agents to discover and invoke backend tools over MCP JSON-RPC while enforcing 3-legged OAuth 2.0 identity propagation, role-based access control, and protocol transcoding to REST APIs.

Enables AI agents to manage tasks through a structured lifecycle (todo, in_progress, ai_testing, manual_testing, deployment, completed) with human approval gates, providing a single-user task management system with CLI, REST API, and live updates.

Enables AI coding agents to request a second opinion from a different frontier model via a single tool call, with PII scrubbed before transit, live web search, and support for Claude, ChatGPT, Cursor, and Gemini.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.