svg-generator-mcp
Generates SVGs from text prompts and converts raster images to SVG using the Quiver AI API.
README
SVG Generator
Generate SVGs from text prompts or convert raster images to SVG using the Quiver AI API.
Works as a cross-platform AI agent skill (Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf) and as an MCP server (Claude Code, Codex, Cursor, Cline, Roo Code, Claude Desktop).
Prerequisites
Get an API key from Quiver AI and set it as an environment variable:
export QUIVER_API_KEY="your-api-key-here"
Installation
Claude Code (Plugin)
claude plugin add /path/to/cc-skills-svg-generator
This installs both the skill (prompt-driven usage) and the MCP server (tool-based usage).
Claude Code (MCP Server only)
claude mcp add svg-generator -- uvx svg-generator-mcp
Claude Code (Skill only)
Copy or symlink the svg-generator/ directory into your skills folder:
# User-level (all projects)
cp -r svg-generator ~/.claude/skills/svg-generator
# Project-level (this project only)
mkdir -p .claude/skills
cp -r svg-generator .claude/skills/svg-generator
OpenAI Codex CLI
As a skill:
mkdir -p .agents/skills
cp -r svg-generator .agents/skills/svg-generator
As an MCP server — add to ~/.codex/config.toml:
[mcp_servers.svg-generator]
command = "uvx"
args = ["svg-generator-mcp"]
enabled = true
Cursor
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"svg-generator": {
"command": "uvx",
"args": ["svg-generator-mcp"],
"env": {
"QUIVER_API_KEY": "your-api-key-here"
}
}
}
}
Cline / Roo Code
Add via the MCP settings panel, or add to the MCP config file:
{
"mcpServers": {
"svg-generator": {
"command": "uvx",
"args": ["svg-generator-mcp"],
"env": {
"QUIVER_API_KEY": "your-api-key-here"
}
}
}
}
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"svg-generator": {
"command": "uvx",
"args": ["svg-generator-mcp"],
"env": {
"QUIVER_API_KEY": "your-api-key-here"
}
}
}
}
Install from PyPI
pip install svg-generator-mcp
Or run directly with uvx:
uvx svg-generator-mcp
MCP Server Tools
The MCP server exposes two tools:
generate_svg
Generate SVGs from text descriptions.
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt |
string | Yes | Text description of the SVG |
output |
string | No | Output filename |
output_dir |
string | No | Output directory (default: .) |
instructions |
string | No | Style guidance |
references |
string[] | No | Reference image URLs (max 4) |
n |
int | No | Number of SVGs, 1-16 (default: 1) |
temperature |
float | No | Randomness 0-2 (default: 1) |
model |
string | No | Model name (default: arrow-preview) |
timeout |
int | No | Request timeout in seconds (default: 600) |
vectorize_svg
Convert raster images (PNG, JPG, WebP) to SVG.
| Parameter | Type | Required | Description |
|---|---|---|---|
image |
string | Yes | Local file path or URL |
output |
string | No | Output filename |
output_dir |
string | No | Output directory (default: .) |
auto_crop |
bool | No | Enable automatic cropping |
target_size |
int | No | Target size in pixels (128-4096) |
n |
int | No | Number of SVGs, 1-16 (default: 1) |
temperature |
float | No | Randomness 0-2 (default: 1) |
model |
string | No | Model name (default: arrow-preview) |
timeout |
int | No | Request timeout in seconds (default: 600) |
CLI Scripts
The skill also includes standalone CLI scripts:
# Text-to-SVG
python3 svg-generator/scripts/generate_svg.py \
--prompt "a minimalist mountain logo" \
--output mountain.svg
# Image-to-SVG
python3 svg-generator/scripts/vectorize_svg.py \
--image photo.png \
--output vectorized.svg
See svg-generator/SKILL.md for full CLI documentation.
Project Structure
.
├── .claude-plugin/
│ └── plugin.json # Claude Code plugin manifest
├── .mcp.json # Project-level MCP config
├── svg-generator/
│ ├── SKILL.md # Cross-platform agent skill
│ ├── references/
│ │ └── api_reference.md
│ └── scripts/
│ ├── generate_svg.py
│ └── vectorize_svg.py
├── src/
│ └── svg_generator_mcp/
│ ├── __init__.py
│ └── server.py # MCP server implementation
├── pyproject.toml # Python package config
└── svg-generator.skill # Packaged skill (zip)
How It Works
| Layer | What | Reaches |
|---|---|---|
Skill (SKILL.md) |
Instructions + CLI scripts the AI follows | Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, GitHub Copilot |
| MCP Server | Structured tool API over Model Context Protocol | Claude Code, Claude Desktop, Codex CLI, Cursor, Cline, Roo Code |
Plugin (.claude-plugin/) |
Bundles skill + MCP server config | Claude Code |
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.