Skip to main content

MCP Server

AI Assistant Integration

Connect Claude, ChatGPT, and other AI assistants to our geocoding API using the Model Context Protocol (MCP)

✨ Latest Version: Streamable HTTP Transport

Now using the modern MCP 2025-03-26 specification - simpler setup, no Node.js required for Cursor/Claude!

What is MCP?

The Model Context Protocol (MCP) is a standardized way for AI assistants to interact with external tools and services. Our MCP server allows AI assistants like Cursor, Claude, and others to use our geocoding API directly.

✨ Modern Protocol: Uses Streamable HTTP transport (MCP 2025-03-26 specification)

🔑 Same Authentication: Uses your existing API keys with full rate limiting

Server Information

MCP Server URL

https://mcp.geocodercloud.com

Authentication

API key required in X-API-Key header

Available Tools

  • geocode_address - Convert addresses to coordinates
  • standardize_address - Parse and standardize addresses

Transport Protocol

Streamable HTTP (MCP 2025-03-26 specification)

Performance

Production-ready with reliable connection handling

Quick Start

1

Get Your API Key

Sign up and create an API key in your dashboard.

2

Configure Your AI Assistant

Add the MCP server configuration to your AI assistant settings.

3

Start Geocoding

Ask your AI assistant to geocode addresses!

Setup Instructions

Claude Desktop supports MCP servers via Streamable HTTP. Simple URL-based configuration:

1 Edit Claude Configuration

Add to your Claude Desktop configuration file:

{
  "mcpServers": {
    "geocoder-cloud": {
      "url": "https://mcp.geocodercloud.com/mcp",
      "headers": {
        "X-API-KEY": "gck_your_api_key_here"
      }
    }
  }
}

📍 Configuration location:
Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2 Restart Claude Desktop

Completely close and reopen Claude Desktop to load the MCP server.

⚠️ Important: Replace gck_your_api_key_here with your actual API key from the dashboard.

Example prompts to try:

  • "What are the coordinates for 1600 Pennsylvania Ave NW, Washington, DC?"
  • "Geocode the address: 350 5th Ave, New York, NY"
  • "Standardize this address: 1 apple park way cupertino california"
  • "Find me the location of the Empire State Building"

💡 Pro Tip: Once configured, Claude will automatically use the geocoding tools when you ask location-related questions!

Cursor IDE natively supports MCP servers via Streamable HTTP. Simple URL-based configuration - no Node.js required!

1 Edit MCP Configuration File

Open or create ~/.cursor/mcp.json and add:

{
  "mcpServers": {
    "geocoder-cloud": {
      "url": "https://mcp.geocodercloud.com/mcp",
      "headers": {
        "X-API-KEY": "gck_your_api_key_here"
      }
    }
  }
}

💡 That's it! Just URL + API key. Cursor handles the Streamable HTTP protocol automatically.

2 Restart Cursor

Completely close and reopen Cursor IDE to load the new MCP server.

3 Verify Connection

Check Cursor's MCP logs to verify the connection:

~/.cursor-server/data/logs/*/exthost*/anysphere.cursor-mcp/

⚠️ Important: Replace gck_your_api_key_here with your actual API key from the dashboard.

Why This Setup is Better

  • No Node.js or npm installation required
  • Direct HTTP connection - more reliable
  • Simpler configuration - just URL + headers
  • Uses modern Streamable HTTP transport (MCP 2025-03-26 spec)
  • Faster connection establishment

How to use in Cursor:

  1. Open the AI chat panel in Cursor (Cmd+L or Ctrl+L)
  2. The geocoder tools will be available to the AI assistant
  3. Ask questions like:
    • "What are the coordinates for the White House?"
    • "Geocode: 350 5th Ave, New York, NY"
    • "Standardize the address: 1 apple park way cupertino ca"
  4. The AI will automatically use the geocoding tools to answer

💡 Pro Tip: You can use the geocoding tools while coding to validate addresses, get coordinates for testing, or standardize address formats in your codebase!

To use with ChatGPT or OpenAI-powered applications, use the main Geocoding API:

ℹ️ Note: OpenAI GPTs and Custom Actions use REST APIs. Use the main Geocoding API at https://www.geocodercloud.com for these integrations.

1 Using with OpenAI API / GPTs

Configure the Geocoding API as an external tool in your OpenAI application:

{
  "type": "function",
  "function": {
    "name": "geocode_address",
    "description": "Geocode a US address to coordinates",
    "parameters": {
      "type": "object",
      "properties": {
        "address": {
          "type": "string",
          "description": "The US address to geocode"
        }
      },
      "required": ["address"]
    }
  },
  "api": {
    "url": "https://www.geocodercloud.com/api/v1/geocode",
    "method": "POST",
    "headers": {
      "X-API-Key": "gck_your_api_key_here"
    },
    "json_body": {
      "address": "{address}"
    }
  }
}

2 Using with Custom GPTs

Create a Custom GPT and add this action:

  • Geocode Address
    • Method: POST
    • URL: https://www.geocodercloud.com/api/v1/geocode
    • JSON body: {"address":"{address}"}

3 Authentication Setup

Configure authentication for your Custom GPT:

  • Authentication Type: API Key
  • Auth Type: Custom
  • Header Name: X-API-Key
  • API Key: gck_your_api_key_here

4 Using with OpenAI Assistants API

Add as a function in your Assistant:

import openai

# Create assistant with geocoding tool
assistant = openai.beta.assistants.create(
    name="Geocoding Assistant",
    instructions="You are a helpful assistant that can geocode addresses.",
    model="gpt-4-turbo-preview",
    tools=[{
        "type": "function",
        "function": {
            "name": "geocode_address",
            "description": "Geocode a US address to get coordinates",
            "parameters": {
                "type": "object",
                "properties": {
                    "address": {"type": "string"}
                },
                "required": ["address"]
            }
        }
    }]
)

# In your tool call handler:
import requests

def handle_geocode(address):
    response = requests.post(
        "https://www.geocodercloud.com/api/v1/geocode",
        headers={"X-API-Key": "gck_your_api_key_here"},
        json={"address": address}
    )
    return response.json()

⚠️ Important: Replace gck_your_api_key_here with your actual API key from the dashboard.

Example prompts for your Custom GPT:

  • "Find the coordinates for 1600 Pennsylvania Ave NW, Washington, DC"
  • "Geocode this address: 350 5th Ave, New York, NY"
  • "Standardize: one apple park way cupertino california"
  • "What's the location of the Statue of Liberty?"

💡 Pro Tip: You can create a Custom GPT specifically for geocoding and share it with your team! Perfect for real estate, logistics, and location-based applications.

📚 Documentation: For more details on OpenAI function calling, visit the OpenAI Function Calling Guide.

Direct API Usage

The MCP server uses the Streamable HTTP transport protocol (MCP 2025-03-26 specification). All communication happens through the /mcp endpoint using JSON-RPC messages.

💡 For Direct API Calls: If you need REST-style endpoints, use the main Geocoding API at https://www.geocodercloud.com instead. See the API Documentation for details.

Geocode an Address (Main API)

curl -X POST "https://www.geocodercloud.com/api/v1/geocode" \
  -H "X-API-Key: gck_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{"address":"1600 Pennsylvania Ave NW"}'

📚 Learn More: For complete API documentation including response formats, rate limits, and advanced features, visit the Interactive API Documentation.

Features

  • Same API key authentication
  • Respects your rate limits
  • Two powerful geocoding tools
  • Production-ready and secure
  • Full error handling

Security

  • API key authentication required
  • Rate limiting enforced
  • Email verification required
  • HTTPS encryption
  • Usage tracking & monitoring

Rate Limits

The MCP server uses the same rate limits as the main API based on your subscription tier:

Developer

5,000

requests per month

Property Pro

50,000

requests per month

Growth

500,000

requests per month

Enterprise

1,000,000+

requests per month

Ready to Get Started?

Sign up now and start using our MCP server with your AI assistant!