About SVGL MCP Server
SVGL MCP Server lets MCP clients validate SVG markup and browse or retrieve SVGs from the SVGL repository. It also returns line-level validation errors and base64-encoded SVG content.
Key features
- 01Validate SVG against SVGL specifications
- 02Browse repository SVGs and metadata
- 03Report validation errors by line
- 04Retrieve SVGs as base64
Use cases
- 01Check SVG markup for specification errors
- 02Find SVGs by repository metadata
- 03Retrieve SVG content for embedding
MCP support
It exposes SVG validation and repository access tools to MCP clients, including listing and retrieving SVGs.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMESVGL MCP Server
An MCP server implementation that processes SVG content using SVGL (Scalable Vector Graphics Language), providing validation and repository access capabilities.
Features
- SVG Validation: Validate SVG content against SVGL specifications
- SVG Repository Access: Browse and retrieve SVGs from the SVGL repository
- Detailed Error Reporting: Get line-by-line validation feedback
- Base64 Encoding: Get SVGs encoded in base64 format for easy embedding
Tools
-
svgl_validate
- Validate SVG content against SVGL specifications
- Inputs:
svgContent(string): SVG content to validate
- Returns detailed validation results including line numbers and error messages
-
svgl_list
- List all SVGs in the repository with their metadata
- Returns an array of SVG items with:
id: Unique identifiertitle: SVG titlecategory: SVG categoryroute: SVG route (string or object with light/dark variants)url: SVG URL
-
svgl_get
- Retrieve a specific SVG by name
- Inputs:
name(string): The name of the SVG to retrieve
- Returns the SVG content in base64 format if valid
Usage with Claude Desktop
Add this to your claude_desktop_config.json:
Docker
{
"mcpServers": {
"svgl": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/svgl"]
}
}
}
NPX
{
"mcpServers": {
"svgl": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-svgl"]
}
}
}
Usage with VS Code
For quick installation, use the one-click installation buttons below...
For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open User Settings (JSON).
Optionally, you can add it to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.
Note that the
mcpkey is not needed in the.vscode/mcp.jsonfile.
Docker
{
"mcp": {
"servers": {
"svgl": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/svgl"]
}
}
}
}
NPX
{
"mcp": {
"servers": {
"svgl": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-svgl"]
}
}
}
}
Build
Docker build:
docker build -t mcp/svgl:latest -f src/svgl/Dockerfile .
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Comments
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.