Gyazo MCP Server Integration

What does “Gyazo” MCP Server do?

The Gyazo MCP (Model Context Protocol) Server is a TypeScript-based tool that enables AI assistants to access and interact with Gyazo images seamlessly through the Model Context Protocol. It acts as a bridge between AI clients and the Gyazo image hosting service, exposing Gyazo images as resources and providing various tools for searching, fetching, uploading, and managing image content and metadata. By integrating Gyazo with development workflows, this MCP server empowers AI assistants to automate tasks such as retrieving recent screenshots, searching images by keyword or metadata, and uploading new images—all while preserving important contextual information like OCR data and image provenance. This enhances productivity and enables richer, image-driven AI interactions in environments that support MCP.

List of Prompts

No prompt templates are explicitly mentioned in the repository.

List of Resources

• Gyazo Images via gyazo-mcp:// URIs
  Access and list Gyazo images as standardized resources.
• Image Metadata
  Each image resource includes metadata such as title, description, app, and URL.
• Image Content (Original format)
  Provides access to the original image content (JPEG, PNG, etc.).
• OCR Data
  If available, OCR (optical character recognition) text associated with the image is included.

List of Tools

• gyazo_search
  Perform full-text searches for captures uploaded by users on Gyazo. Search by keyword, title, app, URL, or date range; supports pagination and returns matching image URIs with metadata.
• gyazo_image
  Fetch specific image content and metadata from Gyazo by image ID or URL.
• gyazo_latest_image
  Retrieve the most recent image from Gyazo, including image content, metadata, and OCR text if available.
• gyazo_upload
  Upload a new image to Gyazo using base64-encoded data, with optional metadata such as title, description, referer URL, and app name; returns a permalink URL and image ID.

Use Cases of this MCP Server

• Automated Screenshot Retrieval
  Developers or AI agents can automatically fetch the latest screenshots taken with Gyazo for documentation, bug reporting, or sharing visual progress.
• Image Search and Discovery
  Enables searching a user’s Gyazo library for relevant images using keywords, metadata, or OCR text, aiding in quick access to visual assets.
• Image Upload and Annotation
  Facilitates programmatic uploading of new images from local or remote sources, while adding contextual metadata for organization and collaboration.
• Metadata Extraction and Organization
  Retrieve and utilize detailed metadata (like titles, descriptions, and app sources) for cataloging or integrating images into external systems.
• AI-Driven Visual Workflows
  Integrate Gyazo images into AI-powered workflows for tasks such as visual analysis, content generation, or enrichment with OCR data.

How to set it up

Windsurf

No Windsurf-specific instructions are provided in the repository.

Claude

1. Prerequisite: Obtain your Gyazo API access token and set it as the GYAZO_ACCESS_TOKEN environment variable.
2. Locate your Claude Desktop configuration file:
   • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%/Claude/claude_desktop_config.json
3. Add the Gyazo MCP Server configuration:

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

4. Save the file and restart Claude Desktop.
5. Verify that the MCP server is connected and operational.

Securing API Keys

• API keys are secured using environment variables in the configuration:

  "env": {
    "GYAZO_ACCESS_TOKEN": "your-access-token-here"
  }
  

Cursor

No Cursor-specific instructions are provided in the repository.

Cline

No Cline-specific instructions are provided in the repository.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "gyazo-mcp-server": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “gyazo-mcp-server” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots support: ⛔ (No mention in available documentation/repository)

Based on the available documentation and repository contents, the Gyazo MCP Server clearly exposes its core tools and resources, provides clear setup instructions for Claude, and uses secure API key handling. However, there is a lack of information for other platforms (Windsurf, Cursor, Cline), no prompt templates or roots/sampling info, and limited explicit resource descriptions beyond images.

Overall, for a typical image-centric MCP use case, this repository is solid for Claude integration, but would benefit from more cross-platform and advanced MCP feature documentation.

MCP Score

Our opinion:
I would rate the Gyazo MCP Server a 6/10 for general MCP server utility. It is well-documented for Claude and has useful tools for Gyazo image workflows, but lacks prompt templates, cross-platform instructions, and explicit support for advanced MCP features like roots and sampling, which limits its versatility for broader MCP adoption.