DiagramZu
diagramzu-mcp lets an AI client (Claude, Cursor, ChatGPT, etc.) author Mermaid diagrams in a shared workspace that a team can read, comment on, embed, and present at a clean URL — rather than just generating a one-off diagram. Hosted endpoint https://mcp.diagramzu.ai/mcp or local npx -y @diagramzu/mcp. Also listed in the official MCP registry as ai.diagramzu/mcp.
README
@diagramzu/mcp
MCP server for diagramzu.ai. Lets Claude Code, Claude Desktop, Cursor, Windsurf, ChatGPT custom GPTs, and any MCP client read and write Mermaid diagrams in your Space.
You author diagrams by talking to your AI — it stores them at diagramzu.ai/d/<id>, where your team can read and share them.
Available in the official MCP Registry as
ai.diagramzu/mcp.
1. Get a token
Sign up at diagramzu.ai, then create an API token at diagramzu.ai/app/settings/tokens. Tokens look like dz_live_… and are scoped to one Space — no separate space-id needed.
2. Connect your client
The hosted server is the easy path: no install, no build. Just paste a config.
Claude Code
claude mcp add --scope user --transport http diagramzu https://mcp.diagramzu.ai/mcp \
--header "Authorization: Bearer dz_live_xxx"
Claude Desktop, Cursor, Windsurf, Cline
Add to your client's MCP config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS for Claude Desktop, ~/.cursor/mcp.json for Cursor, etc.):
{
"mcpServers": {
"diagramzu": {
"type": "http",
"url": "https://mcp.diagramzu.ai/mcp",
"headers": { "Authorization": "Bearer dz_live_xxx" }
}
}
}
ChatGPT custom GPT (Actions)
In the GPT builder, add an MCP server action pointing to https://mcp.diagramzu.ai/mcp with a Bearer-token authentication header set to your dz_live_… token.
Local stdio (for clients that don't speak remote MCP)
npx -y @diagramzu/mcp
with environment:
DIAGRAMZU_BASE_URL=https://diagramzu.ai
DIAGRAMZU_API_TOKEN=dz_live_xxx
DIAGRAMZU_SPACE_ID=<your space id>
Most users should prefer the remote HTTP transport above — the stdio path exists for clients without HTTP MCP support.
Tools
| Tool | Description |
|---|---|
list_diagrams |
List diagrams in the Space (filter with q, sort by updated / created) |
list_folders |
List folders in the Space |
get_diagram |
Fetch one diagram by id (returns title + Mermaid source) |
create_diagram |
Create a new diagram (returns the share URL) |
update_diagram |
Update title and/or Mermaid source of an existing diagram |
analyze_diagram |
Get a structural summary of a diagram (nodes, edges, density) |
list_versions |
List version history for a diagram |
get_version |
Fetch a specific historical version of a diagram |
Show off your setup
If you publish your MCP / Claude Code config in a dotfiles or example repo, drop this in the README so the next person knows where the diagrams come from:
[](https://diagramzu.ai)
Renders as a small shields-style badge — gray MCP + indigo diagramzu.
Local development (this repo)
For hacking on diagramzu itself, build from source:
cd packages/mcp-diagramzu
pnpm install
pnpm run build
# point your client at: node dist/index.js
# with DIAGRAMZU_BASE_URL / DIAGRAMZU_API_TOKEN / DIAGRAMZU_SPACE_ID
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。