gyazo-mcp-server
by: yuiseki
A Model Context Protocol server for Gyazo
📌Overview
Purpose: To provide a Model Context Protocol server for integrating Gyazo images, allowing AI assistants to interact with Gyazo images seamlessly.
Overview: The gyazo-mcp-server is a TypeScript-based solution that facilitates access to Gyazo images via the Model Context Protocol. It enables applications to retrieve and work with image resources, enhancing functionality through metadata and content sharing with intelligent systems.
Key Features:
-
Resources: Provides access to Gyazo images via
gyazo-mcp://
URIs, delivering original content, metadata (including title, description, app, URL), and optional OCR data for various image formats (JPEG, PNG, etc.). -
Tools: Offers the
gyazo_latest_image
functionality to fetch the most recent Gyazo image, returning both content and metadata, including any available OCR text.
gyazo-mcp-server
A Model Context Protocol server for Gyazo image integration, developed in TypeScript. This server enables AI assistants to access and interact with Gyazo images through the Model Context Protocol.
Features
Resources
- List and access Gyazo images via
gyazo-mcp://
URIs - Each image includes:
- Original image content
- Metadata (title, description, app, URL)
- OCR data (if available)
- Supports various image formats (JPEG, PNG, etc.)
Tools
gyazo_latest_image
: Fetch the most recent image from Gyazo, returning both image content and metadata along with OCR text if available.
Development
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
Docker
To build the Docker image:
npm run image:build
Installation
Prerequisites
- Create a Gyazo account: Gyazo
- Obtain your Gyazo API access token: Gyazo API
- Set the
GYAZO_ACCESS_TOKEN
environment variable with your token.
Claude Desktop Integration
To configure the server for use with Claude Desktop, add the following to your configuration file:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"gyazo-mcp-server": {
"command": "/path/to/gyazo-mcp-server/build/index.js",
"env": {
"GYAZO_ACCESS_TOKEN": "your-access-token-here"
}
}
}
}
Docker Configuration
For Docker integration, use the following configuration:
{
"mcpServers": {
"gyazo-mcp-server": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GYAZO_ACCESS_TOKEN",
"gyazo-mcp-server"
],
"env": {
"GYAZO_ACCESS_TOKEN": "your-access-token-here"
}
}
}
}
Debugging
For debugging, utilize the MCP Inspector, which can be run as a package script:
npm run inspector
The Inspector will provide a URL for debugging tools in your browser.