How to Use the Google Roads MCP in Claude Code

Q: Can I run automated speed limit checks with Google Roads in Claude Code?

Yes, Claude Code calls getsnappedspeedlimits to match your tracking logs with official speed limits. You can script this in your terminal to run as a daily cron job.

Q: How do I add this MCP Server to my Claude Code installation?

Run claude mcp add --transport http google-roads-mcp -- in your terminal. You can verify the installation and list the available tools using the claude mcp list command.

Run terminal-based road snapping and speed limit audits directly from your command line with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Roads MCP to Claude Code

Create your Vinkius account to connect Google Roads to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Google Roads with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process GPS tracks from the terminal.

Pipe raw GPS logs directly into Claude Code's MCP server to clean up tracking drift. The CLI agent triggers `snap_to_roads` to snap coordinate arrays to actual roads and outputs the clean geometries. This terminal-first approach lets you run batch-processing scripts. You can format the output as GeoJSON and save the clean paths directly to your workspace.

Run speed audits via Claude Code's MCP Server.

Use Claude Code to audit speed compliance from the terminal. The agent uses `get_snapped_speed_limits` to match coordinates to roads and pull speed limits in km/h. It can also query `get_speed_limits` using place IDs to check legal speeds on specific segments, writing the results directly to stdout or a local CSV.

Resolve isolated coordinates to road segments.

When parsing log files, Claude Code uses `get_nearest_roads` to map individual, non-continuous coordinates to their closest streets. This is perfect for analyzing scattered ping logs. The CLI agent reads the raw coords, queries the tool, and prints the matching place IDs and street offsets right in your terminal.

Setup guide

Set up Google Roads MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see google-roads-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Google Roads transactions." It will automatically discover and invoke the available Google Roads tools.

Terminal

claude mcp add --transport http google-roads-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Google Roads MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "google-roads-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Google Roads. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Google Roads now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Google Roads MCP in Claude Code

You can feed raw coordinates to Claude Code through your terminal, and it will use `snap_to_roads` to process the path. The CLI agent prints the clean, snapped coordinates directly to stdout.

Yes, Claude Code calls `get_snapped_speed_limits` to match your tracking logs with official speed limits. You can script this in your terminal to run as a daily cron job.

Run `claude mcp add --transport http google-roads-mcp -- ` in your terminal. You can verify the installation and list the available tools using the `claude mcp list` command.

Yes, Claude Code can read a file of up to 100 coordinates and invoke `get_nearest_roads` in a single pass. It then formats the place IDs and outputs them to your terminal.

No, all coordinate payloads and speed limit queries are routed through the secure sandbox. Your raw telemetry data is processed in-memory and is never stored on disk.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript