Vizdown-MCP
The Vizdown-MCP server converts Markdown files containing diagram definitions into various visual formats using Mermaid.js and custom SVG renderers.
Render a single diagram (
render_diagram): Convert the first diagram block found in a.mdfile or raw text into SVG, PNG, JPEG, or PDF, with options for light/dark theme, default/hand-drawn style, and resolution scaling.Render all diagrams (
render_all_diagrams): Process every diagram block in a Markdown file or raw text at once, optionally saving outputs to a specified directory with auto-generated filenames.List diagrams without rendering (
list_diagrams): Scan a Markdown file or raw text and return metadata (type, start/end line) for every detected diagram block — useful for inspection before rendering.20+ diagram types supported: Flowcharts, sequence, class, ER, state, Gantt, git graphs, pie charts, timelines, user journeys, mind maps, architecture/service diagrams, kanban boards, C4 diagrams, quadrant charts, sankey, xychart, block diagrams, and more.
Flexible output & theming: Export as SVG (default), PNG, JPEG, or PDF with configurable resolution scaling; choose between light/dark themes and default/hand-drawn visual styles.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Vizdown-MCP render the flowchart in auth_flow.md as a PNG"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Clarity-beta
Clarity-beta is an MCP server that converts Markdown files into beautiful diagrams — flowcharts, mind maps, architecture diagrams, ER diagrams, Gantt charts, sequence diagrams, and more. Built with Apple HIG design language.
Installation
git clone https://github.com/rutika196/clarity-beta.git
cd clarity-beta
python3 -m venv .venv
source .venv/bin/activate # macOS / Linux
# .venv\Scripts\activate # Windows
pip install -e .
playwright install chromiumRelated MCP server: Markdown + Mermaid to PDF MCP Server
IDE Setup
Cursor
Create or edit .cursor/mcp.json in your project root:
{
"mcpServers": {
"clarity-beta": {
"command": "/absolute/path/to/clarity-beta/.venv/bin/python",
"args": ["-m", "src.server"],
"cwd": "/absolute/path/to/clarity-beta"
}
}
}Replace
/absolute/path/to/clarity-betawith your actual project path.
VS Code
Create .vscode/mcp.json in your project root:
{
"servers": {
"clarity-beta": {
"command": "/absolute/path/to/clarity-beta/.venv/bin/python",
"args": ["-m", "src.server"],
"cwd": "/absolute/path/to/clarity-beta"
}
}
}VS Code reads MCP config from
.vscode/mcp.json— no need to touchsettings.json.
IntelliJ IDEA / WebStorm / PyCharm (JetBrains)
JetBrains IDEs (2025.1+) support MCP via the AI Assistant plugin.
Go to Settings → Tools → AI Assistant → MCP Servers.
Click + Add and fill in:
Field | Value |
Name |
|
Command |
|
Arguments |
|
Working Directory |
|
Or edit the MCP config file directly at ~/.config/jetbrains/mcp.json:
{
"mcpServers": {
"clarity-beta": {
"command": "/absolute/path/to/clarity-beta/.venv/bin/python",
"args": ["-m", "src.server"],
"cwd": "/absolute/path/to/clarity-beta"
}
}
}Windows users: replace
.venv/bin/pythonwith.venv\\Scripts\\python.exeand use\\in paths.
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"clarity-beta": {
"command": "/absolute/path/to/clarity-beta/.venv/bin/python",
"args": ["-m", "src.server"],
"cwd": "/absolute/path/to/clarity-beta"
}
}
}Usage
As a standalone server (stdio transport)
source .venv/bin/activate
clarity-beta
# or
python -m src.serverMCP Tools
render_diagram
Render the first diagram found in a Markdown file or raw text.
Parameter | Type | Default | Description |
| string | — | Path to a |
| string | — | Raw markdown with a diagram block |
| string |
|
|
| string |
|
|
| string |
|
|
| int |
| Resolution multiplier for PNG/JPEG |
render_all_diagrams
Render every diagram block in a file. Same parameters plus output_dir to save files.
list_diagrams
List detected diagram blocks with types and line numbers, without rendering.
Supported Diagram Types
Via Mermaid.js (Playwright)
flowchart, sequence, class, ER, state, gantt, gitGraph, pie, timeline, quadrant, sankey, xychart, block-beta, architecture-beta, kanban, journey, C4
Custom SVG Renderers
Mind maps — balanced horizontal tree with organic Bézier connectors
Architecture / service diagrams — Miro-style auto-layout with icons, step badges, groups
Examples
See the examples/ folder — 13 ready-to-render Markdown files:
File | Diagram Type |
| Flowchart (OAuth 2.0 + MFA) |
| Sequence diagram |
| State diagram |
| ER diagram |
| Class diagram |
| Gantt chart |
| Pie chart |
| Git graph |
| Timeline |
| User journey |
| Mind map (custom SVG) |
| Architecture (17 services + groups) |
| Architecture (CI/CD pipeline) |
Running Tests
python tests/test_all.pyDependencies
mcp[cli]— MCP Python SDKplaywright— Headless Chromium for Mermaid rendering and PNG/JPEG exportcairosvg— SVG to PDF conversionPillow— Image processing (optional, for JPEG)
Available Tools
3 toolslist_diagramsA
List all detected diagram blocks without rendering them.
Args: file_path: Path to a .md file. raw_markdown: Raw markdown string.
Returns: List of dicts with diagram_type, line_start, and line_end for each block.
Inputs: file_path, raw_markdown. Returns: result
render_all_diagramsA
Render ALL diagram blocks found in a Markdown file.
Parses the entire document, finds every diagram block, renders each separately, and optionally saves output files.
Args: file_path: Path to a .md file. raw_markdown: Raw markdown string. output_format: "svg", "png", "jpeg", or "pdf". theme: "light" or "dark". look: "default" or "handDrawn". scale: Resolution multiplier for raster output. output_dir: Directory to save rendered files. Files are named {stem}{type}{index}.{format}.
Returns: List of result dicts, each with diagram_type, index, and base64 output.
Inputs: file_path, raw_markdown, output_format, theme, +3 more. Returns: result
render_diagramA
Render the first diagram found in a Markdown file or raw text.
Args: file_path: Path to a .md file containing a diagram block. raw_markdown: Raw markdown string with a diagram code block. output_format: "svg" (default), "png", "jpeg", or "pdf". theme: "light" (default) or "dark". look: "default" or "handDrawn" (Mermaid sketch mode). scale: Resolution multiplier for PNG/JPEG (default 2).
Returns: Dict with diagram_type, output_format, and base64-encoded output.
Inputs: file_path, raw_markdown, output_format, theme, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools have overlapping purposes that could cause confusion: 'render_all_diagrams' and 'render_diagram' both render diagrams with similar parameters, differing only in whether they process all diagrams or just the first one. 'list_diagrams' is distinct for listing without rendering, but the two render tools have unclear boundaries that might lead to misselection.
All tool names follow a consistent snake_case pattern with clear verb_noun structure: 'list_diagrams', 'render_all_diagrams', and 'render_diagram'. The naming is predictable and readable throughout the set.
Three tools is a reasonable count for a diagram rendering server, allowing for listing and rendering operations. It's slightly thin but covers core functionality without being excessive for the apparent scope.
The tool set covers listing and rendering diagrams with various output options, but there are notable gaps: no tools for updating, deleting, or managing diagram content directly (e.g., editing or validating diagrams), which limits lifecycle coverage for the domain.
Maintenance
Related MCP Connectors
Generate dynamic Mermaid diagrams and charts with AI assistance. Customize styles and export diagr…
Render, verify, describe, and safely edit Mermaid diagrams through MCP.
Publish markdown documents as public share links with mermaid diagrams. Built by AutEng.ai
Make editable flowcharts, process charts, funnels, timelines and data models from plain language.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables the dynamic generation of various software development diagrams, such as flowcharts, sequence diagrams, and architecture diagrams, using Mermaid syntax. It includes tools for diagram validation and provides instructions for exporting results to multiple formats including SVG and PNG.-
- AlicenseNot gradedqualityDmaintenanceConverts Markdown files and standalone Mermaid diagrams into high-quality PDF or PNG documents using Puppeteer and SVG rendering. It supports custom CSS styling and provides tools for professional document generation from markdown-based content.4MIT
- AlicenseNot gradedqualityDmaintenanceEnables creating, manipulating, and managing Mermaid diagrams with automatic saving and multi-format conversion from JSON, CSV, Python, Markdown, and plain text.10MIT
- AlicenseNot gradedqualityDmaintenanceConverts Markdown text into interactive mind maps, supporting export as PNG, JPG, and SVG images.15 npm5MIT