Search, fetch, upload, and interact with Gyazo images, including metadata and OCR data.
A Model Context Protocol server for Gyazo image integration
This is a TypeScript-based MCP server that provides access to Gyazo images. It allows AI assistants to access and interact with Gyazo images through the Model Context Protocol, providing:
gyazo-mcp://
URIsgyazo_search
- Full-text search for captures uploaded by users on Gyazo
gyazo_image
- Fetch image content and metadata from Gyazo
gyazo_latest_image
- Fetch the most recent image from Gyazo
gyazo_upload
- Upload an image to Gyazo
The easiest way to install the Gyazo MCP server is via npm:
npm install -g @notainc/gyazo-mcp-server
http://localhost
for the Callback URLGYAZO_ACCESS_TOKEN
environment variable with your tokenTo use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"gyazo-mcp-server": {
"command": "npx",
"args": ["@notainc/gyazo-mcp-server"],
"env": {
"GYAZO_ACCESS_TOKEN": "your-access-token-here"
}
}
}
}
{
"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"
}
}
}
}
Install dependencies:
npm ci
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
npm run image:build