How does authentication work?
Authentication is handled via OAuth 2.1 – your browser opens for a one-time consent flow, then you're connected.
@OliverGrabner
基本信息
🔌MCP server that gives AI coding agents a visual architecture canvas
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"composer": {
"type": "http",
"url": "https://mcp.usecomposer.com"
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,直接连接服务器端点实时获取工具列表。
Composer is a visual system design tool that gives AI coding agents an architecture canvas to design, visualize, and evolve software architecture diagrams through the Model Context Protocol (MCP). It integrates directly with your IDE, allowing agents to add services, databases, queues, and connections, with a live canvas at usecomposer.com updating in real-time.
Connect your IDE by adding an MCP server using HTTP transport to https://mcp.usecomposer.com. For example, in Claude Code run claude mcp add --transport http composer https://mcp.usecomposer.com. Your browser will open for OAuth authorization on first use. Then use tools like create_diagram, upsert_node, upsert_edge, etc., via your AI coding agent.
Authentication is handled via OAuth 2.1 – your browser opens for a one-time consent flow, then you're connected.
Your diagram data lives on Composer's servers. The MCP server itself is stateless.
The MCP server uses HTTP transport (URL: https://mcp.usecomposer.com). Some IDEs support an alternative stdio transport via npx (e.g., Codex: `codex mcp add composer -- npx -y @usecomposer/mcp --stdio`).
Composer is a dedicated architecture canvas that integrates with any MCP-compatible AI coding agent, providing specialized tools for system design and visualization.
The README does not specify explicit limits. It notes that the server is stateless and data is hosted remotely.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
A curated list of references for MLOps

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
A search tool helps dev to solve the naming things problem.
评论