广告合作
MCP.so
登录

Kroki MCP Server

@utain

代码仓库

基本信息

分类

其他

许可证

MIT

传输方式

stdio

作者

utain

关于 Kroki MCP Server

Kroki-MCP is a Go-based Model Context Protocol tool that converts textual diagram definitions (PlantUML, Mermaid, and more) into images via a Kroki backend. Designed for simplicity and flexibility, it supports both local and remote Kroki servers, offers configurable settings, and

#plantuml-diagrams#kroki#model-context-protocol#mcp-server#model-context-protocol-servers#mcp-go#diagram-mcp#uml-mcp

Kroki MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "kroki-mcp": {
      "command": "go",
      "args": [
        "run",
        "github.com/utain/kroki-mcp/cmd/kroki-mcp@latest",
        "-m",
        "stdio",
        "-f",
        "png",
        "--kroki-host",
        "https://kroki.io"
      ]
    }
  }
}

Kroki MCP Server 工具

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。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Kroki-MCP?

Kroki-MCP is a command-line tool and MCP (Model Context Protocol) server that converts textual diagrams – like PlantUML and Mermaid – into images using a Kroki backend. It supports both local and remote Kroki servers and offers flexible configuration with multiple output formats. It is intended for developers and teams who want to generate diagram images programmatically or integrate diagram generation into MCP-aware environments.

How to use Kroki-MCP?

Kroki-MCP is installed and run via the Go toolchain or Docker. Invoke it with kroki-mcp and specify output format (--format), mode (--mode, either sse or stdio), and Kroki host (--kroki-host). To use it as an MCP server, add a configuration entry in your MCP client’s settings file (e.g., claude_desktop_config.json) pointing to the kroki-mcp command with appropriate arguments.

Key features of Kroki-MCP

  • Two operation modes: SSE (server-sent events) and STDIO (stdin/stdout)
  • Output formats: PNG (default), SVG, JPEG, and PDF
  • Configurable Kroki backend host (default: https://kroki.io)
  • Extensible design for additional diagram types and formats
  • MCP integration via github.com/mark3labs/mcp-go
  • Supports both local and remote Kroki servers

Use cases of Kroki-MCP

  • Convert text-based diagrams (e.g., PlantUML, Mermaid) to images in CI/CD pipelines
  • Provide diagram generation as an MCP tool within MCP-aware assistants or editors
  • Render diagrams from source code repositories for documentation previews
  • Test diagram rendering by pointing to a local Kroki server in a Docker development environment

常见问题

1

What transports does Kroki-MCP support?

Kroki-MCP supports two transports: SSE (Server-Sent Events) and STDIO (standard input/output). The default mode is STDIO.

2

What output formats are available?

Supported output formats are PNG (default), SVG, JPEG, and PDF. Use the `--format` flag to choose one.

3

Can I use a local Kroki server instead of the public one?

Yes. Use the `--kroki-host` flag to specify a custom Kroki server URL. For example, `--kroki-host http://localhost:8000`.

4

How do I run Kroki-MCP inside an MCP client?

Add a `kroki-mcp` entry to your MCP client’s configuration file, specifying the `command` (e.g., `go` or the binary path) and `args` including `run`, the module path, `-m stdio`, `-f png`, and `--kroki-host`. Example configuration is provided in the README.

5

What are the runtime dependencies?

Kroki-MCP requires Go 1.22 or later to build/run from source. A Dockerfile and docker-compose.yml are provided for containerized development and deployment. No additional runtime dependencies are mentioned beyond these and the network access to a Kroki server.

评论

其他 分类下的更多 MCP 服务器

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

Klarix Intelligence Engine

Klarix

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.

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

广告合作