Kroki-MCP

Created By
utaina year ago
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 outputs multiple formats – making it ideal for developers building AI
Overview

What is Kroki-MCP?

Kroki-MCP is a command-line tool and MCP integration that converts textual diagrams (like PlantUML and Mermaid) into images using a Kroki backend.

How to use Kroki-MCP?

To use Kroki-MCP, run the command-line interface with options to specify the output format and mode. For example, you can use kroki-mcp --format svg to convert a diagram to SVG format.

Key features of Kroki-MCP?

  • Supports multiple output formats: PNG, SVG, JPEG, PDF.
  • Can operate in different modes: SSE (Server-Sent Events) and STDIO.
  • Configurable backend host for Kroki server.
  • Extensible to support more diagram types and output formats.
  • Integrates with MCP for diagram conversion.

Use cases of Kroki-MCP?

  1. Converting UML diagrams from PlantUML to images.
  2. Generating visual representations of Mermaid diagrams.
  3. Integrating diagram generation into automated workflows using MCP.

FAQ from Kroki-MCP?

  • Can Kroki-MCP convert all types of diagrams?

Yes, it supports various diagram types as long as they are compatible with the Kroki backend.

  • Is there a graphical interface for Kroki-MCP?

No, Kroki-MCP is a command-line tool designed for integration into other systems.

  • How do I run Kroki-MCP as an MCP server?

You can run it using the command: go run github.com/utain/kroki-mcp/cmd/kroki-mcp@latest --mode sse --format png --kroki-host https://kroki.io.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
utain
Star
0
Language
Go
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago