# Mapillary MCP for AI Agents AI Agent Connect > Mapillary MCP gives your agent direct access to the world's largest street-level imagery platform. Search for specific geographic areas to find high-quality street photos, traffic sign inventories, and connected image sequences. It's built for anyone who needs to pull real-world visual data for urban planning, GIS studies, or navigation development without manually browsing maps. ## Overview - **Category:** image-video - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_B442verPH186qvVTZbo63Sx80S9hDy2EioTaFfgM/ai-agent-connect - **Tags:** street-view, computer-vision, spatial-imagery, mapping, gps-data, traffic-signs ## Description Imagine you're trying to audit every stop sign in a specific city district. Instead of manually scrolling through maps and saving hundreds of images, you can just ask your agent to do it. This Connector connects your AI client to Mapillary, letting it see the world through high-resolution street imagery. You can ask for photos from specific bounding boxes, pull out the exact GPS coordinates of a captured image, or find entire sequences of images that follow a specific driving route. It's incredibly useful for gathering data on road markings and traffic infrastructure. Because Vinkius makes it so easy to manage these connections, you can get this data into your project in seconds. Whether you're building a navigation app or conducting a study on urban sprawl, you're moving from manual searching to automated data gathering. You get the raw data, including metadata, coordinates, and object detections, directly in your chat interface. It takes the friction out of spatial data collection. ## Tools ### 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. ### 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. ### get_map_features Search for traffic signs and road markings in an area to build infrastructure inventories. It helps you catalog road features quickly. ### 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. ### 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. ### search_sequences Locate all image sequences that pass through a specific geographic area. This is perfect for finding continuous routes in a region. ### 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. ## Prompt Examples **Prompt:** ``` Find street-level images in central London. ``` **Response:** ``` I found over 500 images in the central London area. These cover major streets like Oxford Street and the Thames embankment. Each result includes: - **GPS Coordinates** - **Capture Date** - **Compass Angle** - **Sequence ID** ``` **Prompt:** ``` Search for traffic signs in São Paulo. ``` **Response:** ``` I've located over 200 traffic signs in São Paulo. The results include: - **Speed Limits**: 40km/h, 60km/h - **Signs**: Stop signs, yield signs - **Zones**: No-parking areas Each entry comes with GPS coordinates and a confidence score for the detection. ``` **Prompt:** ``` Get object detections for image abc123. ``` **Response:** ``` For image abc123, I found 8 specific detections: - Regulatory: Maximum speed limit 50 - Information: Parking zone - Warning: Curve left - Object: Street light I also have the geometry and confidence scores for each of these. ``` ## Capabilities ### Search street images by area Find street-level photos within a specific geographic bounding box. ### Retrieve image metadata Get GPS coordinates, capture dates, and compass angles for specific images. ### Locate image sequences Identify connected images along specific driving routes in an area. ### Inventory traffic signs Search for and list detected traffic signs and road markings by location. ### Extract object detections Get a list of all detected objects within a specific street-level image. ### Get precise GPS data Access exact coordinates and altitude for any captured street image. ## Use Cases ### Traffic Sign Audit An urban planner needs to find every stop sign in a neighborhood. They ask the agent to search for traffic signs in a specific area and get a list of coordinates. ### Navigation Mapping A developer wants to see the visual context of a new route. They ask the agent to find image sequences passing through a specific highway. ### Environmental Study A researcher needs to find images of specific road markings in a rural area. They use a bounding box search to find all relevant street-level photos. ### Infrastructure Inventory A city official wants to know the types of road signs in a district. They ask the agent to pull object detections from a set of images to see the variety of signs. ## Benefits - Get precise GPS coordinates and compass angles for any image using get_image to build accurate spatial maps. - Automate traffic sign inventory by searching for road markings and objects across large areas with get_map_features. - Pull entire driving routes instantly using search_sequences to see how images connect along a path. - Extract specific object data like speed limits or stop signs from images using get_image_detections for data analysis. - Save hours of manual searching by using search_images to find every photo taken within a specific city block or district. ## How It Works The bottom line is you get to turn natural language into precise street-level data queries. 1. Subscribe to the Mapillary MCP on Vinkius. 2. Enter your Mapillary access token in the configuration. 3. Ask your agent to find images or features in a specific location. ## Frequently Asked Questions **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**](https://www.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.