mcpField
L
logoloom

logoloom

Local
github.com/mcpwareMedia & Design53Updated 31w ago

About logoloom

LogoLoom is a locally running, open-source MCP server that designs logos and exports a complete brand kit. It targets indie developers and small projects, with Claude reading the codebase to write SVG logos that are then converted, optimized and exported as 31 files.

Key features

  1. 01AI-generated logo as clean SVG code
  2. 02Text-to-path conversion for consistent font rendering
  3. 03SVG optimization to reduce file size
  4. 04Export of PNG, ICO, WebP and social media sizes
  5. 05BRAND.md with colors and typography notes
  6. 06Bitmap-to-SVG vectorization with optional system tools

Use cases

  1. 01Creating a logo and favicon for a side project
  2. 02Generating GitHub, OG and Twitter header images
  3. 03Exporting brand assets for a project locally

MCP support

This project is an MCP server that exposes text_to_path, optimize_svg, export_brand_kit and image_to_svg tools to clients such as Claude Code and Cursor.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

LogoLoom

One command. Full brand kit. Zero cost. Stop juggling 5 tools for your logo.

npm npm downloads license

LogoLoom brand kit output

The Problem

Getting a logo for your side project shouldn't cost $96 (Looka) or require juggling Canva + favicon generator + OG image maker + manual PNG exports. Logo is the #1 shipping blocker for indie devs — not because it's hard, but because the tooling sucks.

The Solution

AI designs your logo as clean SVG code (not messy auto-traced paths), then post-processes into a complete brand kit — 31 files, one command:

  • SVG — full logo, icon only, wordmark only (light/dark/mono variants)
  • PNG — 10 standard sizes (16px favicon → 1024px App Store)
  • ICO — browser favicon
  • WebP — web optimized
  • Social — OG image (1200×630), GitHub preview (1280×640), Twitter header (1500×500)
  • BRAND.md — color codes, typography, usage guidelines

Zero API cost. Everything runs locally. Free forever.

Why Not Use Existing Tools?

ToolPriceSVG?Full brand kit?MCP?Local?
LogoLoomFree✅ clean code✅ 31 files✅✅
Looka$65-96✅✅ (templates)❌❌
Brandmark$35-95✅✅ ($95)❌❌
Canva$15/mo for SVGraster only free✅ (Pro)❌❌
Recraft V3Free = no commercial use✅❌❌❌
SVGMaker MCPcredits ($)✅ cloud❌✅❌

What it does

  1. AI designs your logo — Claude reads your codebase, understands your brand, writes SVG
  2. Text → Path — converts <text> to <path> so fonts render everywhere (opentype.js)
  3. Optimize — cleans SVG, removes bloat, compresses paths (SVGO)
  4. Export brand kit — 31 files across 3 categories (full logo + icon only + wordmark only) × (light/dark/mono) + all PNG sizes + social media sizes + BRAND.md

Quick Start

npx @mcpware/logoloom
Claude Code / Cursor .mcp.json
{
  "mcpServers": {
    "logoloom": {
      "command": "npx",
      "args": ["-y", "@mcpware/logoloom"]
    }
  }
}

Then ask Claude: "Design a logo for my project"

Tools

ToolWhat it does
text_to_pathConvert SVG <text> elements to <path> using font outlines. Font-independent rendering.
optimize_svgClean and compress SVG (30-60% smaller). Remove metadata, merge paths.
export_brand_kitExport full brand kit: PNG sizes, ICO, WebP, OG image, mono variants, BRAND.md.
image_to_svgConvert PNG/JPG to SVG vector (vtracer). Best for logos and flat graphics.

Example Output

brand/
├── logo-full-light.svg      # Primary logo
├── logo-full-dark.svg       # Dark mode variant
├── icon-light.svg           # Icon only
├── icon-mono-black.svg      # Single-color (print)
├── icon-mono-white.svg      # White on dark
├── icon-256.png             # Small
├── icon-512.png             # Medium
├── icon-1024.png            # Large (app stores)
├── icon-512.webp            # Web optimized
├── favicon.ico              # Browser favicon
├── favicon-16.png           # 16px favicon
├── favicon-48.png           # 48px favicon
├── og-image.png             # Social share (1200×630)
└── BRAND.md                 # Colors, typography, usage rules

How it works

You: "Design a logo for mcpware"

Claude:
  1. Reads your README + package.json
  2. Asks brand questions (audience, feel, color)
  3. Generates 6-8 SVG concepts in HTML preview
  4. You pick → Claude iterates → you approve

LogoLoom MCP:
  5. text_to_path → font-independent SVG
  6. optimize_svg → clean, compressed
  7. export_brand_kit → all sizes, all formats, brand guidelines

Output: brand/ folder, ready to use everywhere

Why not just use Recraft / SVGMaker?

LogoLoomRecraft V3SVGMaker
PriceFreeFree (no commercial) / $10/mo$8+
Commercial useYesPaid onlyYes
Runs locallyYesNo (cloud)No (cloud)
MCP nativeYesNoYes
Full brand kitYesNo (SVG only)No
Codebase-awareYesNoNo

Tech Stack

All open source, all running locally:

  • opentype.js — font parsing, text → SVG path conversion
  • SVGO — SVG optimization and compression
  • sharp — SVG → PNG/WebP/ICO rasterization
  • vtracer — bitmap → SVG vectorization (optional, needs system install)

Requirements

  • Node.js 18+
  • For image_to_svg: install vtracer (cargo install vtracer) or potrace (apt install potrace)

More from @mcpware

ProjectWhat it doesInstall
Instagram MCP23 Instagram Graph API tools — posts, comments, DMs, stories, analyticsnpx @mcpware/instagram-mcp
Claude Code OrganizerVisual dashboard for Claude Code memories, skills, MCP servers, hooksnpx @mcpware/claude-code-organizer
UI AnnotatorHover labels on any web page — AI references elements by namenpx @mcpware/ui-annotator
PagecastRecord browser sessions as GIF or video via MCPnpx @mcpware/pagecast

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.