How to Use the Mapillary MCP in Claude

Q: How do I search for images in a specific neighborhood using Mapillary on Claude Desktop?

Use the searchimages tool by providing a bounding box with minimum and maximum longitude and latitude. Claude Desktop will return matching image IDs, capture dates, and compass angles for that specific area.

Q: Can I view the actual image files through Mapillary in Claude Desktop?

Yes, getimage returns thumbnail URLs along with capture metadata. Claude Desktop displays these URLs in the chat window so you can inspect the actual street-level view immediately.

Q: Can Claude Desktop identify specific traffic sign types using this toolset?

Yes, getdetectionvalue retrieves the specific classification, coordinates, and associated image for any detected object. Claude Desktop uses this data to verify the exact type of traffic sign present at a location.

Pull Mapillary street-level imagery and traffic sign detections directly into Claude Desktop to audit road assets in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapillary MCP to Claude Desktop

Create your Vinkius account to connect Mapillary to Claude Desktop 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 Mapillary with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map road assets inside Claude Desktop

`get_map_features` grabs spatial data like traffic signs and road objects directly inside Claude Desktop. Your agent queries specific geographic coordinates to identify physical assets without manual field surveys. This MCP Server delivers raw coordinates and confidence scores for every detected object. This means your Claude Desktop agent builds structured lists of physical infrastructure in seconds.

Audit street-level sequences in your chat

`search_sequences` lets your agent find continuous driving routes and image paths within a bounding box. Claude Desktop uses this spatial sequence data to track how road conditions change over time. Once the agent identifies a path, `get_sequence` retrieves the chronologically ordered images. You can inspect construction progress or road wear without switching to a map browser.

Analyze physical detections with this MCP Server

`get_image_detections` extracts traffic signs and road markings from specific image IDs during your chat. Your Claude Desktop agent reads these visual detections to flag missing or damaged street signs. You get raw coordinate geometry and confidence scores for each object. This MCP Server runs in a secure V8 sandbox on Vinkius, keeping your API tokens safe while Claude queries the map database.

Setup guide

Set up Mapillary MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Mapillary MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Mapillary MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under mapillary-mcp.

json

{
  "mcpServers": {
    "mapillary-mcp": {
      "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 Mapillary. 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 Mapillary 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 Mapillary MCP in Claude Desktop

Use the `search_images` tool by providing a bounding box with minimum and maximum longitude and latitude. Claude Desktop will return matching image IDs, capture dates, and compass angles for that specific area.

Yes, `get_image` returns thumbnail URLs along with capture metadata. Claude Desktop displays these URLs in the chat window so you can inspect the actual street-level view immediately.

Vinkius manages the connection to the Mapillary API, meaning your Claude Web client doesn't need to handle complex authentication handshakes. If you hit API limits, the server returns standard error responses that your agent can read and retry.

Yes, `get_detection_value` retrieves the specific classification, coordinates, and associated image for any detected object. Claude Desktop uses this data to verify the exact type of traffic sign present at a location.

Your Mapillary API keys are stored securely on Vinkius and never exposed to the client. The coordinate queries you send to `get_map_features` run in an ephemeral, zero-trust V8 sandbox that destroys all session data as soon as the tool execution finishes.

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