Gyazo MCP Server

What is Gyazo MCP Server about?

Provides AI assistants with direct access to Gyazo image libraries through Model Context Protocol. Images are exposed as resources with gyazo-mcp:// URIs, allowing retrieval of original content, metadata, and OCR data.

How to use Gyazo MCP Server?

1. Install the server globally (or run via npx):

   npm install -g @notainc/gyazo-mcp-server
   

2. Obtain a Gyazo API access token and set it in the environment:

   export GYAZO_ACCESS_TOKEN=your-access-token
   

3. Start the server with npx (recommended):

   npx @notainc/gyazo-mcp-server
   

4. Add the server to Claude Desktop (or any MCP‑compatible client) with a config such as:

   {
     "mcpServers": {
       "gyazo-mcp-server": {
         "command": "npx",
         "args": ["@notainc/gyazo-mcp-server"],
         "env": { "GYAZO_ACCESS_TOKEN": "your-access-token" }
       }
     }
   }
   

Key Features

• Resources: Access Gyazo images via gyazo-mcp:// URIs, each containing original image data, metadata (title, description, app, URL), and OCR text when available.
• Tools:
  • gyazo_search: Full‑text search across a user's Gyazo captures, supporting keyword, title, app, URL, date range, and pagination.
  • gyazo_image: Retrieve a specific image by ID or URL, returning both content and detailed metadata.
  • gyazo_latest_image: Get the most recent capture, including OCR text if present.
  • gyazo_upload: Upload a base64‑encoded image with optional metadata (title, description, referer URL, app name) and receive the permalink and ID.
• Formats: Supports JPEG, PNG, and other common image types.
• Docker support: Optional containerized deployment.

Use Cases

• AI assistants: Enable conversational agents to fetch, display, or analyze Gyazo images while responding to user queries.
• Content management: Automate retrieval of screenshots or visual assets stored in Gyazo for documentation or reporting.
• Searchable knowledge base: Leverage OCR data to make image‑based information searchable within AI workflows.
• Rapid image sharing: Allow AI‑driven tools to upload generated or processed images directly to Gyazo.

FAQ

Q: How do I get a Gyazo API token? A: Log into Gyazo, go to API → Register applications, create a new app (Callback URL can be http://localhost), then generate and copy the access token.

Q: What environment variable is required? A: GYAZO_ACCESS_TOKEN must contain the Gyazo API token.

Q: Does the server return OCR text? A: Yes, when OCR data is available for an image, it is included in the resource metadata and in the gyazo_latest_image tool.

Q: Can I run the server in Docker? A: Yes, use the provided Docker command in the README or build the image with npm run image:build.

Q: Is authentication needed per request? A: No additional per‑request auth is required; the server uses the token set in GYAZO_ACCESS_TOKEN.

gyazo-mcp-server

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:

• Resources representing Gyazo images with URIs and metadata
• Tools for searching, fetching, and uploading images
• Image content and metadata access via the Gyazo API

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_search - Full-text search for captures uploaded by users on Gyazo

  • Search by keyword, title, app, URL, or date range
  • Supports pagination for browsing multiple results
  • Returns matching image URIs and metadata

• gyazo_image - Fetch image content and metadata from Gyazo

  • Retrieve specific images by ID or URL
  • Returns both image content and detailed metadata

• gyazo_latest_image - Fetch the most recent image from Gyazo

  • Returns both image content and metadata
  • Includes OCR text if available

• gyazo_upload - Upload an image to Gyazo

  • Upload images with base64 encoded image data
  • Add optional metadata like title, description, referer URL, and app name
  • Returns the uploaded image's permalink URL and ID

Installation

NPM Package

The easiest way to install the Gyazo MCP server is via npm:

npm install -g @notainc/gyazo-mcp-server

Prerequisites

• Create a Gyazo account if you don't have one: https://gyazo.com
• Get your Gyazo API access token from: https://gyazo.com/api
  • Click "Register applications" button
  • Click "New Application" button
  • Fill in the form with your app name and description
    • Name and Callback URL are required
    • You can use http://localhost for the Callback URL
  • Click "Submit" button
  • Click application name to view details
  • Scroll down to "Your Access Token"
  • Click "Generate" button
  • Copy "Your access token" value
• Set the GYAZO_ACCESS_TOKEN environment variable with your token

Claude Desktop Integration

To 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

Using NPM package (recommended)

{
  "mcpServers": {
    "gyazo-mcp-server": {
      "command": "npx",
      "args": ["@notainc/gyazo-mcp-server"],
      "env": {
        "GYAZO_ACCESS_TOKEN": "your-access-token-here"
      }
    }
  }
}

Using Docker (optional)

{
  "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"
      }
    }
  }
}

Development

Install dependencies:

npm ci

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Docker Build (optional)

npm run image:build

---