Google Roads Connector for AI agents.
4 live capabilities
Snap GPS coordinates to road geometries and retrieve real-time speed limits.
Waiting for input…
Why people use Google Roads
Google Roads for Precise Fleet Telemetry and Map Matching
This Connector handles that heavy lifting for you. By snapping those raw pings to the actual road geometry, your agent produces clean, usable tracks instantly. You get smooth routes and accurate data without the manual cleanup.
What Vinkius changes
You get clean, road-aligned GPS data and speed limits through a simple chat interface.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Fleet Speed Compliance
A manager asks the agent to check if a truck stayed under the speed limit on a specific route using get_snapped_speed_limits.
- Real-world use case 02
Smooth Route Visualization
A developer wants to turn a jagged GPS trail from a bike ride into a smooth line on a map using snap_to_roads.
- Real-world use case 03
Accident Safety Audit
An analyst asks for the speed limits of a road where a collision occurred to see if the driver was speeding using get_speed_limits.
Complete set · 4capabilities
The complete Google Roads capability set.
These are the exact actions your AI can choose when you ask it to work with Google Roads.
01—04
4 capabilities in this set.
Part of 4 available through Google Roads.
- 01 Capability
Get nearest roads
Identifies the closest road segment for individual GPS points that do not form a continuous path.
- 02 Capability
Snap to roads
Matches GPS paths to roads with interpolated points and place IDs for smooth route reconstruction.
- 03 Capability
Get snapped speed limits
Snaps coordinates to roads and returns the posted speed limits in a single request.
- 04 Capability
Get speed limits
Pulls speed limit values for specific road segments using their unique place IDs.
Set up in minutes
One URL. Then ask Google Roads to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Google Roads from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_icL7P1wSdhqlP5hejAj1lwlYwJ0IrlWvNXEfqUmc/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Google Roads, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Google Roads for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_icL7P1wSdhqlP5hejAj1lwlYwJ0IrlWvNXEfqUmc/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Google Roads URL.
- Step 03
Save and start
Save the connection and enable Google Roads in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"google-roads": {
"url": "https://edge.vinkius.com/vk_preview_icL7P1wSdhqlP5hejAj1lwlYwJ0IrlWvNXEfqUmc/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Google Roads
Open Agent mode in chat and ask: "Using Google Roads, help me...". 4 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"google-roads": {
"url": "https://edge.vinkius.com/vk_preview_icL7P1wSdhqlP5hejAj1lwlYwJ0IrlWvNXEfqUmc/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Google Roads
Ask Copilot: "Using Google Roads, help me...". 4 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"google-roads": {
"url": "https://edge.vinkius.com/vk_preview_icL7P1wSdhqlP5hejAj1lwlYwJ0IrlWvNXEfqUmc/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Google Roads
Open Cascade and ask: "Using Google Roads, help me...". 4 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"google-roads": {
"url": "https://edge.vinkius.com/vk_preview_icL7P1wSdhqlP5hejAj1lwlYwJ0IrlWvNXEfqUmc/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Google Roads
Ask Cline: "Using Google Roads, help me...". 4 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add google-roads --transport http "https://edge.vinkius.com/vk_preview_icL7P1wSdhqlP5hejAj1lwlYwJ0IrlWvNXEfqUmc/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Google Roads
Ask Claude: "Using Google Roads, show me...". 4 tools are ready
Where the request belongs
Work Google Roads can move forward.
This is for anyone who deals with GPS data that looks like a mess. It's built for people who need to turn raw telemetry into clean, usable map data without manual cleanup.
Fleet Manager
Monitoring driver speed compliance and cleaning vehicle telemetry to see where trucks actually spent their time.
Mapping Developer
Converting jagged GPS traces from mobile apps into smooth, drivable lines for map visualization.
Safety Analyst
Retrieving speed limit data for specific segments to audit driver behavior during incidents.
GIS Professional
Snapping scattered survey points to the nearest road network for spatial analysis and cartography.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsHERE (Location & Maps)
Build with location data via HERE. geocode addresses, calculate routes, track traffic, and get weather.
TomTom
Equip your AI agent with global mapping, routing, and real-time traffic capabilities powered by TomTom.
Geoapify
Access powerful location intelligence. geocoding, routing, place search, and IP tracking directly from your AI agent.
Stadia Maps
Equip your AI with advanced geospatial routing and mapping logic. Calculate distances, geocode coordinates, and plot optimized trips securely.
Jawg Maps (Location & Routing)
Build with location data via Jawg Maps. search places, calculate routes, compute distance matrices, and get elevation data.
Road511
Access real-time US and Canada traffic data via Road511. track incidents, monitor cameras, check road conditions, and analyze trends from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Google Roads connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Google Roads.
The practical details behind the request, access and result.
Can the Google Roads MCP clean up jumpy GPS data?
Yes, it snaps noisy GPS pings to the nearest drivable road geometry. This removes the 'jitter' caused by GPS drift and creates a smooth path for your maps.
How does the Google Roads MCP help with fleet management?
It allows you to see exactly which roads your vehicles traveled on and helps you monitor speed compliance by pulling posted limits for those specific segments.
Can I get speed limits for a specific road with the Google Roads MCP?
Yes, you can pull posted speed limits for road segments using their place IDs. This is great for analyzing driver behavior against legal limits.
Does the Google Roads MCP work for batch coordinates?
Yes, it can handle up to 100 coordinate pairs in a single request. This makes it efficient for processing large sets of telemetry data at once.
Can I use the Google Roads MCP to find the nearest street for a single point?
Yes, the capability can identify the nearest road segment for individual points, even if they aren't part of a continuous path or sequence.
How does the Google Roads MCP handle different road types?
It identifies the most likely roads traveled and provides the corresponding road geometry and posted speed limits, regardless of whether it's an urban or rural road.
Can my AI snap a GPS track to the actual roads travelled?
Yes! Use the snap_to_roads capability with your GPS coordinates in path format (latitude,longitude pairs separated by pipes). For example: path=40.7128,-74.0060|40.7135,-74.0055|40.7142,-74.0048. Set interpolate=true for smoother road geometry with additional interpolated points between your input coordinates. The response includes snapped coordinates, original coordinates, and place IDs for each road segment.
How do I get speed limit data for a specific road segment?
Use the get_speed_limits capability with place IDs obtained from snap_to_roads or get_nearest_roads responses. For example: place_ids=ChIJplaceId1|ChIJplaceId2|ChIJplaceId3. The API returns speed limits in km/h for each road segment. If you need both snapped coordinates AND speed limits in one call, use get_snapped_speed_limits with a GPS path instead.
What is the difference between snap_to_roads and get_nearest_roads?
snap_to_roads assumes your coordinates form a continuous path and snaps them to the most likely sequence of roads travelled, with optional interpolation for smoother geometry. get_nearest_roads treats each coordinate independently and finds the nearest road segment for each point without assuming they form a path. Use snap_to_roads for GPS tracks and routes, and get_nearest_roads for scattered individual points.
One connection away
Give your agent a direct line to Google Roads.
Connect Google Roads once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available