How to Use the Mapillary MCP in Cursor

Q: How does Cursor use Mapillary to find traffic sign detections?

Your Cursor agent calls getimagedetections with an image ID to receive a list of detected objects. It then uses this raw data to generate typed interfaces or database schemas in your project.

Q: Can I test Mapillary image queries locally using this MCP Server inside Cursor?

Yes, by configuring the server in your .cursor/mcp.json file, your agent can run getimage locally. It pulls real thumbnail URLs and compass angles directly into your active chat or terminal session.

Q: What parameters do I need to give Cursor to search Mapillary sequences?

You need to feed searchsequences a bounding box string containing longitude and latitude limits. Cursor passes these coordinates to the server to return all matching sequence IDs in that region.

Q: Can this tool help me write code to classify objects?

Yes, getdetectionvalue provides the classification type and GPS coordinates for individual detections. Your Cursor agent can use these real payloads to write and test your classification logic.

Generate code using real-world street data by connecting Cursor to Mapillary to write apps with live spatial imagery.

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 Cursor

Create your Vinkius account to connect Mapillary to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject real spatial data into your Cursor workspace

`search_images` finds street-level imagery within a bounding box directly from your Cursor agent. This prevents you from writing code against stale mock data or static stubs when building mapping apps. Your agent reads the real coordinate outputs, capture dates, and compass angles returned by the tool. You get working code built around live spatial payloads in real time.

Build asset inventories with this MCP Server

`get_map_features` fetches traffic signs and physical objects by coordinate area to feed your active code files. Cursor's agent mode uses this structured spatial data to write database insertion scripts. Instead of guessing the JSON structure of the API, this MCP Server hands the exact schema to Cursor. Your agent writes accurate parsers for confidence scores and feature types on the first try.

Track image sequences during active coding

`search_sequences` retrieves the paths of driving routes through any geographic area directly into your editor. Cursor uses these sequence IDs to help you write algorithms that trace continuous street paths. By calling `get_sequence` alongside this search, your agent understands the chronological progression of the imagery. You can build and debug routing logic without leaving your workspace.

Setup guide

Set up Mapillary MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Mapillary MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Mapillary transactions." If the MCP tools are loaded correctly, Cursor will call the Mapillary tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Your Cursor agent calls `get_image_detections` with an image ID to receive a list of detected objects. It then uses this raw data to generate typed interfaces or database schemas in your project.

Yes, by configuring the server in your `.cursor/mcp.json` file, your agent can run `get_image` locally. It pulls real thumbnail URLs and compass angles directly into your active chat or terminal session.

You need to feed `search_sequences` a bounding box string containing longitude and latitude limits. Cursor passes these coordinates to the server to return all matching sequence IDs in that region.

Yes, `get_detection_value` provides the classification type and GPS coordinates for individual detections. Your Cursor agent can use these real payloads to write and test your classification logic.

Yes, Vinkius handles your API credentials on its secure backend, so your token is never exposed in your `.cursor/mcp.json` file. All coordinate data sent to `get_map_features` is processed in an isolated sandbox that leaves no persistent logs.

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