mcpField
G
Gemini MCP Server

Gemini MCP Server

Remote
github.com/muckitymuckAI & Agents0Updated 79w ago
Repository

About Gemini MCP Server

Gemini MCP Server analyzes webpages using the Gemini API and stores screenshots with tags and metadata. It is intended for applications that need to inspect pages and retrieve their captured results through an API.

Key features

  1. 01Analyze webpages with Gemini
  2. 02Capture webpage screenshots
  3. 03Attach tags and metadata
  4. 04Retrieve screenshots by ID
  5. 05Filter screenshots by tag or metadata

Use cases

  1. 01Analyze a webpage from its URL
  2. 02Retrieve a previously captured screenshot
  3. 03Find screenshots by tag or page metadata

MCP support

The project identifies itself as an MCP server for webpage analysis, but the README describes HTTP endpoints rather than MCP-specific tools or transport.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://example.com
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Gemini MCP Server

Multi-context processing (MCP) server using Gemini API for analyzing webpages.

Features

  • Screenshot and analyze webpages
  • Tag and metadata for screenshots
  • Retrieve screenshots and associated data via API

API Endpoints

Process a webpage
POST /process

Request body:

{
  "url": "https://example.com",
  "prompt": "Describe what you see on this webpage"
}
Get screenshots
Get screenshot by ID
GET /screenshots/:id

Example:

GET /screenshots/123

Response:

{
  "id": 123,
  "url": "https://example.com",
  "prompt": "Describe what you see on this webpage",
  "created_at": "2023-06-15T12:34:56Z",
  "tags": ["initial_load", "page_entry"],
  "metadata": {
    "pageState": "initial",
    "pageTitle": "Example Domain"
  },
  "download_url": "https://yoursupabaseproject.supabase.co/storage/v1/object/public/screenshots/screenshot_1234.png"
}
Get screenshots with filters
GET /screenshots?tag=initial_load

or

GET /screenshots?key=pageTitle&value=Example%20Domain

Response:

{
  "count": 2,
  "screenshots": [
    {
      "id": 123,
      "url": "https://example.com",
      "prompt": "Describe what you see on this webpage",
      "created_at": "2023-06-15T12:34:56Z",
      "tags": ["initial_load", "page_entry"],
      "metadata": {
        "pageState": "initial",
        "pageTitle": "Example Domain"
      },
      "download_url": "https://yoursupabaseproject.supabase.co/storage/v1/object/public/screenshots/screenshot_1234.png"
    },
    // Additional screenshots...
  ]
}

Installation

  1. Clone the repository
  2. Create a .env file based on .env.example
  3. Run npm install
  4. Run npm run build
  5. Start the server with npm start

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.