Mapillary Connector for AI agents.
7 live capabilities
Access street-level imagery and traffic sign data for urban planning and GIS research.
Waiting for input…
Why people use Mapillary
Mapillary for Street-Level Imagery and Traffic Sign Inventory
This Connector changes that by letting your agent do the heavy lifting. You just describe the area you're interested in, and the agent pulls the data for you. Instead of clicking through a web interface, you get a structured list of signs, images, and coordinates delivered straight to your chat.
What Vinkius changes
You get to turn natural language into precise street-level data queries.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Traffic Sign Audit
An urban planner needs to find every stop sign in a neighborhood.
- Real-world use case 02
Navigation Mapping
A developer wants to see the visual context of a new route.
- Real-world use case 03
Environmental Study
A researcher needs to find images of specific road markings in a rural area.
Complete set · 7capabilities
The complete Mapillary capability set.
These are the exact actions your AI can choose when you ask it to work with Mapillary.
01—04
4 capabilities in this set.
Part of 7 available through Mapillary.
- 01 Capability
Get detection value
Get specific details on a detected object, including its type, value, and GPS coordinates. This is useful for identifying specific traffic signs.
- 02 Capability
Get image
Pull metadata like capture time, compass angle, and thumbnail URLs for a specific image. It provides the full context of a street capture.
- 03 Capability
Get map features
Search for traffic signs and road markings in an area to build infrastructure inventories. It helps you catalog road features quickly.
- 04 Capability
Get sequence
Retrieve details for a specific image sequence, including the creation date and all related images. This helps you see a full driving path.
05—07
3 capabilities in this set.
Part of 7 available through Mapillary.
- 05 Capability
Search images
Find street-level images within a geographic bounding box using min/max longitude and latitude. It is the primary way to find photos in a specific area.
- 06 Capability
Search sequences
Locate all image sequences that pass through a specific geographic area. This is perfect for finding continuous routes in a region.
- 07 Capability
Get image detections
List all objects detected within a single image, including confidence scores and geometry. Use this to see everything an AI spotted in a photo.
Set up in minutes
One URL. Then ask Mapillary to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Mapillary 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_B442verPH186qvVTZbo63Sx80S9hDy2EioTaFfgM/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 Mapillary, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Mapillary for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_B442verPH186qvVTZbo63Sx80S9hDy2EioTaFfgM/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 Mapillary URL.
- Step 03
Save and start
Save the connection and enable Mapillary in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"mapillary": {
"url": "https://edge.vinkius.com/vk_preview_B442verPH186qvVTZbo63Sx80S9hDy2EioTaFfgM/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 Mapillary
Open Agent mode in chat and ask: "Using Mapillary, help me...". 7 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"mapillary": {
"url": "https://edge.vinkius.com/vk_preview_B442verPH186qvVTZbo63Sx80S9hDy2EioTaFfgM/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 Mapillary
Ask Copilot: "Using Mapillary, help me...". 7 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"mapillary": {
"url": "https://edge.vinkius.com/vk_preview_B442verPH186qvVTZbo63Sx80S9hDy2EioTaFfgM/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 Mapillary
Open Cascade and ask: "Using Mapillary, help me...". 7 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"mapillary": {
"url": "https://edge.vinkius.com/vk_preview_B442verPH186qvVTZbo63Sx80S9hDy2EioTaFfgM/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 Mapillary
Ask Cline: "Using Mapillary, help me...". 7 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add mapillary --transport http "https://edge.vinkius.com/vk_preview_B442verPH186qvVTZbo63Sx80S9hDy2EioTaFfgM/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 Mapillary
Ask Claude: "Using Mapillary, show me...". 7 tools are ready
Where the request belongs
Work Mapillary can move forward.
This is for urban planners, GIS researchers, and navigation developers who need to gather real-world visual data at scale without manual clicking.
Urban Planner
They use this to audit traffic sign inventory and road infrastructure across entire city districts.
GIS Researcher
They pull geotagged imagery and spatial data for environmental studies and urban development research.
Navigation Developer
They use it to gather high-quality street photos and object detections to improve mapping accuracy.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsNearmap (High-Res Aerial Imagery & AI)
Manage geospatial data via Nearmap. retrieve high-res aerial imagery, extract AI features, and audit survey coverage.
TomTom
Access global mapping, geocoding, and routing services. Search for addresses, calculate optimal routes, and retrieve map tiles directly through AI.
Mapbox
Integrate Mapbox mapping and location services into your AI agent—access vector/raster tiles, static images, directions, and manage datasets.
ArcGIS
Access GIS services via ArcGIS. geocode addresses, search places, get routes, check elevation and discover basemap styles from any AI agent.
HERE (Location & Maps)
Build with location data via HERE. geocode addresses, calculate routes, track traffic, and get weather.
OpenStreetMap
Access and edit OpenStreetMap data. manage changesets, query map elements, and retrieve geospatial data directly from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Mapillary 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 Mapillary.
The practical details behind the request, access and result.
What can I do with the Mapillary MCP?
You can use it to search for street-level imagery, find specific traffic signs, and pull GPS metadata for photos in almost any geographic area.
Can I use Mapillary to find specific traffic signs?
Yes. You can ask your agent to search for traffic signs in a specific city or district to get a list of detections and their coordinates.
How does Mapillary help with urban planning?
It automates the inventory of road markings and infrastructure, allowing planners to audit large areas without manual site visits.
Can I get GPS coordinates from street images?
Yes, the Connector can pull exact GPS coordinates, compass angles, and capture dates for any specific image in the database.
Is Mapillary good for GIS research?
It's excellent for GIS research because it provides high-resolution, geotagged imagery and spatial data for various urban and environmental studies.
Can I find driving routes using Mapillary?
Yes, you can find and retrieve full sequences of connected images that follow specific driving routes through a geographic area.
How do I get a Mapillary access token?
Sign up at mapillary.com/developer and create an application to get your access token.
What is a bounding box?
A bounding box defines a geographic area using min_longitude, min_latitude, max_longitude, max_latitude. Example: "-0.15,51.50,-0.10,51.52" covers central London.
What map features are available?
Mapillary detects traffic signs (stop, speed limit, yield, etc.), road objects (fire hydrants, mailboxes, etc.) and road markings. Use get_map_features to search by area.
One connection away
Give your agent a direct line to Mapillary.
Connect Mapillary once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available