Media Forge

io.github.PavelGuzenfeldPublished by GitHub account PavelGuzenfeldv0.2.0Updated Nov 10, 2026

MCP server for generating diagrams, charts, presentations, and animations for Markdown documentation

Overview

AI-generated overview

Local MCP server that turns text DSLs into diagrams, charts, self-contained HTML pages and slide decks, returning file paths to embed in Markdown docs.

What you can do
  • Render diagrams from Mermaid, D2 and Graphviz DOT code as SVG or PNG
  • Render Vega-Lite JSON specifications as bar, line, scatter, area or heatmap charts
  • Generate self-contained themed HTML pages with a built-in CSS design system
  • Build HTML slide decks from a JSON slide array with keyboard and touch navigation
  • Read per-tool usage guides and list previously generated assets in the output directory
When to use it
Useful when an assistant writes or maintains Markdown documentation and should add architecture diagrams, dependency graphs, charts, report pages or presentation decks as files in the project rather than inline text.
Requirements
Runs locally over stdio, typically via npx or a cloned and built Node.js package. Diagram and chart tools need a Docker rendering container started separately; HTML page and slide tools work without Docker. Optional environment variables PROJECT_ROOT, OUTPUT_DIR and MEDIA_FORGE_CONTAINER set the output location and container name.
Before you install
Tools write generated files into the project output directory (default docs/generated), so the assistant can create or overwrite assets there. Diagram rendering depends on a Docker container being running; without it those tools fail. Generated HTML pages and slides embed the supplied HTML content, so review output before publishing it.

Installation

In SourceWeft

  1. Open Media Forge in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

MCP Media Forge

[npm] [MCP Registry] [License: MIT]

MCP server that generates diagrams, charts, HTML pages, and slide decks from text DSLs -- designed for AI coding agents to embed into Markdown.

LLM agents call tools like render_mermaid, render_html_page, or render_slides with text input, and get back file paths to assets ready to embed in docs.

Output Gallery

Mermaid Flowchart

[Mermaid flowchart]

Mermaid Sequence Diagram

[Mermaid sequence diagram]

D2 Architecture Diagram

[D2 architecture diagram]

Graphviz Dependency Graph

[Graphviz dependency graph]

Vega-Lite Bar Chart

[Vega-Lite bar chart]

Tools

Diagram & Chart Renderers (Docker)

ToolInputFormatsUse Case
render_mermaidMermaid codeSVG, PNGFlowcharts, sequence, ER, state, Gantt, git graphs
render_d2D2 codeSVG, PNGArchitecture diagrams with containers and icons
render_graphvizDOT codeSVG, PNGDependency graphs, network diagrams
render_chartVega-Lite JSONSVG, PNGBar, line, scatter, area, heatmap charts

HTML Generators (No Docker)

ToolInputOutputUse Case
render_html_pageHTML body + themeSelf-contained HTMLTechnical docs, reports, dashboards
render_slidesJSON slide array + themeHTML slide deckPresentations, status updates, walkthroughs

Utilities

ToolDescription
get_tool_guideUsage examples, anti-patterns, complexity limits per tool
list_assetsList all generated files in the output directory

Quick Start

1. Start the rendering container (for diagram tools)

bash
cd dockerdocker compose up -d

HTML page and slide tools work without Docker.

2. Install the MCP server

Option A -- npx (no install)

bash
npx mcp-media-forge

Option B -- Clone and build

bash
git clone https://github.com/PavelGuzenfeld/mcp-media-forge.gitcd mcp-media-forgenpm installnpm run build

3. Register with your MCP client

Any MCP-compatible client (Claude Code, Cursor, VS Code + Copilot, Cline, etc.) can use this server. The standard config:

json
{  "mcpServers": {    "media-forge": {      "command": "node",      "args": ["/path/to/mcp-media-forge/dist/index.js"],      "env": {        "PROJECT_ROOT": "/path/to/your/project"      }    }  }}

Where to add this depends on your client:

  • Claude Code: ~/.claude/settings.json
  • Cursor: MCP settings panel
  • VS Code (Copilot): .vscode/mcp.json
  • Cline: MCP server configuration

4. Use it

Ask your AI assistant to generate diagrams, pages, or presentations:

"Create a sequence diagram showing the OAuth2 flow and embed it in the README"

"Generate an HTML page summarizing the API architecture with KPI cards"

"Make a slide deck with our Q1 metrics and architecture overview"

The agent calls the appropriate tool, gets back a file path, and embeds it in your markdown.

How It Works

AI Agent (any MCP client)    |    | MCP Protocol (JSON-RPC over stdio)    vMCP Media Forge (Node.js on host)    |    |--- Diagrams: docker exec (sandboxed, no network)    |       |    |       v    |   Rendering Container    |     ├── mmdc       (Mermaid CLI + Chromium)    |     ├── d2         (D2 diagrams)    |     ├── dot/neato  (Graphviz)    |     └── vl2svg     (Vega-Lite via vl-convert)    |    |--- HTML/Slides: template engine (no Docker)    |       |    |       v    |   CSS Design System (4 themes, depth tiers, components)    |    vdocs/generated/  mermaid-a1b2c3.svg  d2-7f8e9a.svg  html_page-d4e5f6.html  slides-8b9c0d.html

Key design decisions:

  • Text in, file path out -- returns relative paths, never base64 blobs
  • Content-hash naming -- same input = same file = free caching + git-friendly
  • SVG preferred -- vector format, small files, diffs cleanly in git
  • Docker-contained -- diagram renderers run in a sandboxed container with network_mode: none
  • Self-contained HTML -- pages and slides have zero external dependencies (inline CSS/JS)
  • Input pre-validation -- catches common mistakes before Docker round-trips
  • Structured errors -- error responses include error_type, error_message, and suggestion to enable LLM self-correction

Tool Reference

get_tool_guide

Get usage guide for any tool before rendering. Returns examples, anti-patterns to avoid, complexity limits, and tips.

json
{ "tool_name": "mermaid" }

Available guides: mermaid, d2, graphviz, vegalite, html_page, slides, or all for a summary.

render_mermaid

json
{  "code": "flowchart TD\n    A[Start] --> B{Decision}\n    B -->|Yes| C[Done]",  "format": "svg",  "theme": "default"}
ParameterTypeDefaultDescription
codestringrequiredMermaid diagram code (must start with diagram type)
formatsvg | pngsvgOutput format
themedefault | dark | forest | neutraldefaultMermaid theme

Pre-validation catches: missing diagram type, semicolons, HTML in labels, >25 nodes.

render_d2

json
{  "code": "client -> server -> database",  "format": "svg",  "layout": "dagre"}
ParameterTypeDefaultDescription
codestringrequiredD2 diagram code
formatsvg | pngsvgOutput format
themenumber--Theme ID (0=default, 1=neutral-grey, 3=terminal)
layoutdagre | elk | taladagreLayout engine

Pre-validation catches: Mermaid/D2 syntax confusion, unbalanced braces, >3 nesting depth.

render_graphviz

json
{  "dot_source": "digraph G { A -> B -> C }",  "engine": "dot",  "format": "svg"}
ParameterTypeDefaultDescription
dot_sourcestringrequiredGraphviz DOT source code
enginedot | neato | fdp | sfdp | twopi | circodotLayout engine
formatsvg | pngsvgOutput format

Pre-validation catches: missing graph wrapper, -> in undirected graphs, unbalanced braces.

render_chart

json
{  "spec_json": "{\"$schema\":\"https://vega.github.io/schema/vega-lite/v5.json\",\"data\":{\"values\":[{\"x\":1,\"y\":10}]},\"mark\":\"bar\",\"encoding\":{\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}}}",  "format": "svg"}
ParameterTypeDefaultDescription
spec_jsonstringrequiredVega-Lite JSON specification
formatsvg | pngsvgOutput format
scalenumber1Scale factor for PNG output

Pre-validation catches: invalid JSON, missing $schema/data/mark, >500 inline data rows.

render_html_page

Generates a self-contained themed HTML page. No Docker required.

json
{  "title": "System Overview",  "body_html": "<section id=\"metrics\"><h2>Metrics</h2><div class=\"mf-grid mf-grid-3\">...</div></section>",  "theme": "swiss",  "description": "Q1 architecture overview",  "nav_sections": ["Metrics", "Architecture", "Roadmap"]}
ParameterTypeDefaultDescription
titlestringrequiredPage title
body_htmlstringrequiredHTML body content (inner content only, no <html>/<head>/<body>)
themeswiss | midnight | warm | terminalswissVisual theme
descriptionstring--Page description (meta tag + header)
nav_sectionsstring[]--Section names for floating IntersectionObserver navigation

Design system CSS classes:

ClassPurpose
mf-heroPrimary highlight section (large shadow)
mf-elevatedSecondary highlight (medium shadow)
mf-cardBordered content card
mf-recessedDe-emphasized content
mf-grid mf-grid-2Responsive 2-column grid
mf-grid mf-grid-3Responsive 3-column grid
mf-splitTwo equal columns
mf-kpi + mf-kpi-value + mf-kpi-labelKey metric display
mf-badge-success/warning/error/infoStatus badges

Themes:

ThemeStyleBest for
swissWhite, geometric, blue accentTechnical docs
midnightDeep navy, serif, gold accentPresentations
warmCream paper, bold sans, terracottaReports
terminalDark, monospace, cyan accentDeveloper content

render_slides

Generates a self-contained HTML slide deck with keyboard/touch navigation. No Docker required.

json
{  "title": "Q1 Review",  "slides": "[{\"title\":\"Q1 Review\",\"content\":\"Engineering update\",\"type\":\"title\"},{\"title\":\"Metrics\",\"content\":\"<ul><li>99.9% uptime</li></ul>\",\"type\":\"content\"}]",  "theme": "midnight",  "author": "Engineering Team"}
ParameterTypeDefaultDescription
titlestringrequiredPresentation title
slidesstringrequiredJSON array of slide objects
themeswiss | midnight | warm | terminalswissVisual theme
authorstring--Author (shown on title slide)

Slide types:

TypeLayoutBest for
titleCentered large text + subtitleOpening/closing slides
sectionCentered heading + descriptionTopic dividers
contentHeading + body (bullets, text)Most content
splitHeading + two columnsBefore/after, comparisons
codeHeading + code blockCode walkthroughs
quoteLarge blockquote + attributionTestimonials, key quotes
kpiHeading + auto-grid metricsDashboards, stats
imageHeading + centered imageScreenshots, diagrams

Navigation: Arrow keys, Space, PageUp/PageDown, Home/End. Touch: swipe left/right. Click dots to jump.

list_assets

json
{ "directory": "" }

Returns a JSON array of all generated files with name, path, size, and modification time.

Error Handling

All tools return structured errors that help LLMs self-correct:

json
{  "status": "error",  "error_type": "syntax_error",  "error_message": "First line must declare diagram type. Got: \"A --> B\"",  "suggestion": "Start with: flowchart TD, sequenceDiagram, erDiagram, ... See https://mermaid.js.org/syntax/"}

Error types: syntax_error, rendering_error, dependency_missing.

Pre-validation catches common LLM mistakes before hitting the renderer:

  • Mermaid: missing diagram type, semicolons, HTML tags, legacy graph syntax
  • D2: Mermaid syntax confusion (-->, subgraph), unbalanced braces
  • Graphviz: missing digraph/graph wrapper, -> in undirected graphs
  • Vega-Lite: invalid JSON, missing required fields, oversized inline data

Environment Variables

VariableDefaultDescription
PROJECT_ROOTcwd()Project root for output path resolution
OUTPUT_DIRdocs/generatedOutput directory relative to PROJECT_ROOT
MEDIA_FORGE_CONTAINERmedia-forge-rendererDocker container name

Development

bash
npm installnpm run build          # Build with tsupnpm run dev            # Watch modenpm test               # Run all tests (95 total)npm run test:unit      # Unit tests only (no Docker needed)npm run test:component # Integration tests (Docker tools need container)npm run lint           # Type-check with tsc

Running integration tests

bash
cd docker && docker compose up -d   # Start renderer (diagram tools only)cd .. && npm run test:component     # All integration tests

HTML page and slide integration tests run without Docker.

Examples

See examples/ for sample input files:

FileToolDescription
mermaid/flowchart.mmdrender_mermaidDecision flowchart
mermaid/sequence.mmdrender_mermaidClient-server sequence
d2/architecture.d2render_d2Backend architecture with containers
graphviz/dependencies.dotrender_graphviznpm dependency graph
vegalite/bar-chart.jsonrender_chartTool performance comparison

See examples/README.md for MCP tool call examples and expected responses.

License

MIT

Source: README.md at commit 315951c

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts