ALT Decision Tree MCP Server
@yamanoku
About ALT Decision Tree MCP Server
Model Context Protocol server that generates appropriate alternative text for images using ALT decision tree
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"alt-decision-tree-mcp-server": {
"command": "deno",
"args": [
"run",
"alt-decision-tree-mcp-server.ts"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is ALT Decision Tree MCP Server?
An MCP server that automatically generates alternative text (ALT attributes) for images by applying the ALT decision tree based on W3C WAI-ARIA guidelines. It is intended for developers and content creators who need to produce accessible, context-aware image descriptions.
How to use ALT Decision Tree MCP Server?
Launch the server with deno run alt-decision-tree-mcp-server.ts. The server exposes two MCP tools: generate_alt_text (accepts base64‑encoded image data, optional context and image format) and get_alt_guidance (provides best practices for writing alt text). Run tests with deno test.
Key features of ALT Decision Tree MCP Server
- Analyzes uploaded images to understand their content.
- Applies the W3C‑based ALT decision tree for alt text generation.
- Considers the image’s purpose and context for appropriate descriptions.
- Returns a confidence score (0–1) for the generated alt text.
- Provides detailed reasoning and decision‑tree steps.
Use cases of ALT Decision Tree MCP Server
- Automating alt text generation for web content management systems.
- Ensuring image accessibility in blogs, e‑commerce, and documentation.
- Assisting developers in meeting WCAG guidelines without manual effort.
- Generating descriptive alt text for complex images like charts or diagrams.
FAQ from ALT Decision Tree MCP Server
What is the ALT decision tree logic?
The server evaluates the image in five stages: whether it is decorative, contains text, is complex (e.g., charts), is informational, or serves a functional purpose. Each stage decides the appropriate type of alt text.
What image formats are supported?
PNG, JPEG/JPG, GIF, and WebP.
What runtime does the server require?
The server is a Deno script and must be run with the Deno runtime.
What tools does the server provide?
Two MCP tools: generate_alt_text (to generate alt text from an image) and get_alt_guidance (to retrieve best practices and guidance on the ALT decision tree).
How is the alt text decision returned?
The generate_alt_text tool returns the generated alt text, the reasoning behind the decision, the decision‑tree steps, and a confidence score between 0 and 1.
Frequently asked questions
What is the ALT decision tree logic?
The server evaluates the image in five stages: whether it is decorative, contains text, is complex (e.g., charts), is informational, or serves a functional purpose. Each stage decides the appropriate type of alt text.
What image formats are supported?
PNG, JPEG/JPG, GIF, and WebP.
What runtime does the server require?
The server is a Deno script and must be run with the Deno runtime.
What tools does the server provide?
Two MCP tools: `generate_alt_text` (to generate alt text from an image) and `get_alt_guidance` (to retrieve best practices and guidance on the ALT decision tree).
How is the alt text decision returned?
The `generate_alt_text` tool returns the generated alt text, the reasoning behind the decision, the decision‑tree steps, and a confidence score between 0 and 1.
Basic information
More Other MCP servers

DeepMark
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
MCP Toolbox for Databases
googleapisMCP Toolbox for Databases is an open source MCP server for databases.
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
ICSS
chokcoco不止于 CSS
Website
FunnyWolfAdversary simulation and Red teaming platform with AI
Comments