Skip to main content
Glama
Sign In
deenesjakoruzh

Street View MCP

by vlad-ds
GitHub
Python
2
OverviewInspectNewSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

Integrations

  • Uses the Google Maps API to fetch Street View data, requiring an API key with Street View API enabled.

  • Enables fetching and displaying Street View imagery by address, coordinates, or panorama ID, saving images to local files, and creating HTML pages that compile multiple Street View images into virtual tours.

Street View MCP

A Model-Client-Protocol (MCP) server for Google Street View API that enables AI models to fetch and display street view imagery and create virtual tours.

Using with Claude Desktop

To use Street View MCP with Claude Desktop:

  1. Ensure you have uv installed: UV Installation Guide
  2. Clone this repository:
    git clone https://github.com/vlad-ds/street-view-mcp.git cd street-view-mcp
  3. Install dependencies:
    uv pip install -e ".[dev]"
  4. Get a Google Maps API key (instructions below)
  5. Add the following to your Claude Desktop claude_desktop_config.json file:
"street_view": { "command": "uv", "args": [ "run", "--directory", "/path/to/street-view-mcp", // Replace with your actual path "mcp", "run", "src/street_view_mcp/server.py" ], "env": { "API_KEY": "your_google_maps_api_key_here" // Add your API key here } }

After configuration, you can use Street View MCP in Claude Desktop simply by typing "/street_view".

Overview

Street View MCP provides a simple interface for AI models to:

  1. Fetch Street View images by address, coordinates, or panorama ID
  2. Save images to local files
  3. Open saved images in the default viewer
  4. Create HTML pages that compile multiple Street View images into virtual tours

Requirements

  • Python 3.9+
  • Google Maps API key with Street View API enabled
  • fastmcp package
  • uv package manager (recommended)

Installation

# Clone the repository git clone https://github.com/vlad-ds/street-view-mcp.git cd street-view-mcp # Create and activate a virtual environment with uv (recommended) uv venv source .venv/bin/activate # On Windows: .venv\Scripts\activate # Install dependencies uv pip install -e ".[dev]"

API Key Setup

The Street View MCP requires a Google Maps API key with Street View API enabled:

  1. Visit the Google Cloud Console
  2. Create a new project or select an existing one
  3. Enable the "Street View Static API" in the API Library
  4. Create an API key from the Credentials page
  5. Set the API key as an environment variable:
# Set temporarily in your shell: export API_KEY=your_api_key_here # Or create a .env file in the project root: echo "API_KEY=your_api_key_here" > .env

Usage

Starting the MCP Server

python -m street_view_mcp.main --host 127.0.0.1 --port 8000

The server will be available to AI models at the specified host and port.

Using as a CLI Tool

# Fetch Street View image by address python -m street_view_mcp.street_view --address "Empire State Building, NY" --output output/empire_state.jpg # Fetch Street View image by latitude/longitude python -m street_view_mcp.street_view --latlong "40.748817,-73.985428" --output output/coords.jpg --heading 180 # Fetch Street View image by panorama ID python -m street_view_mcp.street_view --pano PANO_ID --output output/panorama.jpg

MCP Tools

The Street View MCP provides the following tools for AI models:

get_street_view

Fetches a Street View image based on location, coordinates, or panorama ID and saves it to a file.

{ "filename": "empire_state.jpg", "location": "Empire State Building, NY", "size": "600x400", "heading": 90, "pitch": 10 }

Parameters:

  • filename (required): Name for saving the image (must not already exist)
  • location (optional): Address to get image for
  • lat_lng (optional): Comma-separated coordinates (e.g., "40.748817,-73.985428")
  • pano_id (optional): Specific panorama ID
  • size (optional): Image dimensions as "widthxheight" (default: "600x400")
  • heading (optional): Camera heading in degrees (0-360, default: 0)
  • pitch (optional): Camera pitch in degrees (-90 to 90, default: 0)
  • fov (optional): Field of view in degrees (10-120, default: 90)
  • radius (optional): Search radius in meters (default: 50)
  • source (optional): Image source ("default" or "outdoor", default: "default")

Note: Exactly one of location, lat_lng, or pano_id must be provided.

get_metadata

Fetches metadata about a Street View panorama.

{ "location": "Empire State Building, NY" }

Parameters:

  • Same location parameters as get_street_view
  • Returns JSON metadata with status, copyright, date, panorama ID, and coordinates

open_image_locally

Opens a saved Street View image in the default application.

{ "filename": "empire_state.jpg" }

Parameters:

  • filename (required): The filename of the image to open (must exist in output directory)

create_html_page

Creates an HTML page that displays multiple Street View images as a virtual tour.

{ "filename": "nyc_tour.html", "title": "New York City Tour", "html_elements": [ "<h1>New York City Landmarks Tour</h1>", "<p>Explore famous landmarks through Street View images.</p>", "<h2>Empire State Building</h2>", "<img src='../output/empire.jpg' alt='Empire State Building'>", "<p class='location'>350 Fifth Avenue, New York, NY</p>", "<p class='description'>This 102-story Art Deco skyscraper was completed in 1931.</p>" ] }

Parameters:

  • html_elements (required): List of HTML content elements
  • filename (required): Name for the HTML file
  • title (optional): Page title (default: "Street View Tour")

Important: When referencing images, always use the path ../output/filename.jpg.

Creating Virtual Tours

The Street View MCP enables creation of virtual tours by combining multiple Street View images with descriptive text in an HTML page.

Example workflow for creating a tour:

  1. Fetch images of different locations:
get_street_view(filename="empire.jpg", location="Empire State Building, NY") get_street_view(filename="times_square.jpg", location="Times Square, NY") get_street_view(filename="central_park.jpg", location="Central Park, NY")
  1. Create an HTML tour page:
create_html_page( filename="nyc_tour.html", title="New York City Tour", html_elements=[ "<h1>New York City Landmarks Tour</h1>", "<p>Explore these famous NYC landmarks through Street View images.</p>", "<h2>Empire State Building</h2>", "<img src='../output/empire.jpg' alt='Empire State Building'>", "<p class='location'>350 Fifth Avenue, New York, NY</p>", "<p class='description'>An iconic 102-story Art Deco skyscraper in Midtown Manhattan.</p>", "<h2>Times Square</h2>", "<img src='../output/times_square.jpg' alt='Times Square'>", "<p class='location'>Broadway & 7th Avenue, New York, NY</p>", "<p class='description'>Famous for its bright lights, Broadway theaters, and as the site of the annual New Year's Eve ball drop.</p>", "<h2>Central Park</h2>", "<img src='../output/central_park.jpg' alt='Central Park'>", "<p class='location'>Central Park, New York, NY</p>", "<p class='description'>An urban park spanning 843 acres in the heart of Manhattan.</p>" ] )

Project Structure

  • street_view_mcp/
    • __init__.py: Package initialization
    • main.py: Entry point for MCP server
    • server.py: MCP server implementation
    • street_view.py: Core Street View API client

Important Notes

  • Local Storage: This tool saves all Street View images and HTML files locally in the output/ directory
  • No Automatic Cleanup: There is no built-in mechanism to delete saved files
  • Manual Cleanup: You should periodically clean up the output/ directory to manage disk space
  • API Usage: Each image request counts toward your Google Maps API quota and may incur charges

Development

Testing

pytest

License

MIT

This server cannot be installed

-
security - not tested
F
license - not found
-
quality - not tested

A server that enables AI models to fetch and display Google Street View imagery, allowing users to create virtual tours by viewing streets and landmarks from anywhere.

  1. Using with Claude Desktop
    1. Overview
      1. Requirements
        1. Installation
          1. API Key Setup
            1. Usage
              1. Starting the MCP Server
              2. Using as a CLI Tool
            2. MCP Tools
              1. get_street_view
              2. get_metadata
              3. open_image_locally
              4. create_html_page
            3. Creating Virtual Tours
              1. Project Structure
                1. Important Notes
                  1. Development
                    1. Testing
                  2. License

                    Related MCP Servers

                    • Image Toolkit MCP Server

                      Kira-Pgr
                      -
                      security
                      A
                      license
                      -
                      quality
                      A server that provides AI-powered image generation, modification, and processing capabilities through the Model Context Protocol, leveraging Google Gemini models and other image services.
                      Last updated -
                      6
                      Python
                      MIT License
                      • Linux
                      • Apple

                    • Playwright MCP Server

                      Kotelberg
                      -
                      security
                      F
                      license
                      -
                      quality
                      A server that enables AI systems to browse, retrieve content from, and interact with web pages through the Model Context Protocol.
                      Last updated -

                    • Map Traveler MCP

                      mfukushim
                      A
                      security
                      A
                      license
                      A
                      quality
                      An MCP server that creates a virtual traveling environment on Google Maps, allowing users to guide an avatar on journeys with photo reports and SNS integration.
                      Last updated -
                      2
                      140
                      11
                      TypeScript
                      MIT License
                      • Linux
                      • Apple

                    • Kakao API MCP Server

                      jeong-sik
                      -
                      security
                      A
                      license
                      -
                      quality
                      A server that enables AI models to access Kakao Map features (place search, address lookup, route finding) and Daum search services (web, image, blog, cafe) through Model Context Protocol.
                      Last updated -
                      3
                      TypeScript
                      MIT License

                    View all related MCP servers

                    New MCP Servers

                    ID: cbxo866pjw