Outscraper MCP Server is a streamlined implementation of the Model Context Protocol that provides access to Google Maps data extraction services. It offers two essential tools for extracting business information and reviews with high reliability and advanced filtering capabilities.
To install the Outscraper MCP server for Claude Desktop automatically:
npx -y @smithery/cli install outscraper-mcp --client claude
# Using pip
pip install outscraper-mcp
# Using uv (recommended)
uv add outscraper-mcp
# Using uvx for one-time execution
uvx outscraper-mcp
git clone https://github.com/jayozer/outscraper-mcp
cd outscraper-mcp
# Using uv (recommended)
uv sync
# Using pip
pip install -e .
export OUTSCRAPER_API_KEY="your_api_key_here"
Or create a .env file:
OUTSCRAPER_API_KEY=your_api_key_here
Add to your claude_desktop_config.json:
Via Smithery (Automatic):
{
"mcpServers": {
"outscraper": {
"command": "npx",
"args": ["-y", "@smithery/cli", "run", "outscraper-mcp"],
"env": {
"OUTSCRAPER_API_KEY": "your_api_key_here"
}
}
}
}
Via Local Installation:
{
"mcpServers": {
"outscraper": {
"command": "uvx",
"args": ["outscraper-mcp"],
"env": {
"OUTSCRAPER_API_KEY": "your_api_key_here"
}
}
}
}
Via Manual Installation:
{
"mcpServers": {
"outscraper": {
"command": "uv",
"args": ["run", "python", "-m", "outscraper_mcp"],
"env": {
"OUTSCRAPER_API_KEY": "your_api_key_here"
}
}
}
}
Automatic Installation with UVX (Recommended):
{
"mcpServers": {
"outscraper": {
"command": "uvx",
"args": ["outscraper-mcp"],
"env": {
"OUTSCRAPER_API_KEY": "your_api_key_here"
}
}
}
}
Manual Installation:
{
"mcpServers": {
"outscraper": {
"command": "outscraper-mcp",
"env": {
"OUTSCRAPER_API_KEY": "your_api_key_here"
}
}
}
}
Search for businesses and places on Google Maps
# Parameters:
query: str # Search query (e.g., 'restaurants brooklyn usa')
limit: int = 20 # Number of results (max: 400)
language: str = "en" # Language code
region: str = None # Country/region code (e.g., 'US', 'GB')
drop_duplicates: bool = False # Remove duplicate results
enrichment: List[str] = None # Additional services ['domains_service', 'emails_validator_service']
Extract reviews from Google Maps places
# Parameters:
query: str # Place query, place ID, or business name
reviews_limit: int = 10 # Number of reviews per place (0 for unlimited)
limit: int = 1 # Number of places to process
sort: str = "most_relevant" # Sort order: 'most_relevant', 'newest', 'highest_rating', 'lowest_rating'
language: str = "en" # Language code
region: str = None # Country/region code
cutoff: int = None # Unix timestamp for reviews after specific date
# FastMCP Inspector - Web-based testing dashboard
fastmcp dev outscraper_mcp/server.py
# Then open your browser to: http://127.0.0.1:6274
# Via PyPI installation
outscraper-mcp
# Via uv
uv run python -m outscraper_mcp
# Via manual installation
python -m outscraper_mcp
from outscraper_mcp import mcp
if __name__ == "__main__":
mcp.run(transport="streamable-http", host="127.0.0.1", port=8000)
# 1. Search for restaurants
results = google_maps_search(
query="italian restaurants manhattan nyc",
limit=5,
language="en",
region="US"
)
# 2. Get reviews for a specific place
reviews = google_maps_reviews(
query="ChIJrc9T9fpYwokRdvjYRHT8nI4", # Place ID from search results
reviews_limit=20,
sort="newest"
)
# Find businesses with enhanced contact information
businesses = google_maps_search(
query="digital marketing agencies chicago",
limit=20,
enrichment=["domains_service", "emails_validator_service"]
)
# Get detailed reviews for sentiment analysis
for business in businesses:
if business.get('place_id'):
reviews = google_maps_reviews(
query=business['place_id'],
reviews_limit=10,
sort="newest"
)
# Research competitors in specific area
competitors = google_maps_search(
query="coffee shops downtown portland",
limit=50,
region="US"
)
# Analyze recent customer feedback
recent_reviews = google_maps_reviews(
query="coffee shops downtown portland",
reviews_limit=100,
sort="newest"
)
Import Error: Make sure you've installed the package correctly
pip install --upgrade outscraper-mcp
API Key Error: Verify your API key is set correctly
echo $OUTSCRAPER_API_KEY
No Results: Check if your query parameters are valid
Rate Limits: Implement delays between requests if needed
import logging
logging.basicConfig(level=logging.DEBUG)
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.