How to Use the Mapillary MCP in LangChain

Q: Can a LangChain agent analyze image sequences with Mapillary?

Yes. The agent calls searchsequences to find routes in an area, then uses getsequence to retrieve the chronological image list.

Q: What fields can I request when fetching an image?

Use getimage and pass specific fields like geometry, compass angle, or thumbnail URLs. This limits the payload size to exactly what your agent needs.

Feed real-world street imagery and traffic sign data directly into your LangChain reasoning loops.

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 LangChain

Create your Vinkius account to connect Mapillary to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Locate street-level images using LangChain

`search_images` finds specific street-level imagery within coordinate bounding boxes. Your agent uses this tool to locate the exact image IDs, capture dates, and compass angles for any geographic area you target. LangChain chains pass these image IDs directly to downstream steps in your pipeline. You get raw spatial coordinates and sequence details without writing manual API queries or parsing messy JSON payloads.

Map traffic signs with this MCP Server

`get_map_features` extracts localized traffic sign data and road features by coordinate boundaries. The tool returns exact GPS coordinates and confidence scores for physical assets like stop signs or speed limit markers. Your agent uses these outputs to trigger conditional chains based on detection confidence. You can automatically route low-confidence detections to human review steps while logging high-confidence features directly to your GIS database.

Reconstruct visual driving routes

`search_sequences` identifies continuous driving routes through specific geographic areas. The tool returns sequence IDs that your agent uses to trace the exact path a camera took through a neighborhood. Feeding these IDs into `get_sequence` pulls the ordered list of image frames along that route. Your LangChain agent can step through these frames sequentially to verify road changes over time.

Setup guide

Set up Mapillary MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Mapillary tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "mapillary-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Mapillary transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the adapter package and use the MultiServerMCPClient to connect to the server URL. Call get_tools to fetch the tools and pass them directly to your agent constructor.

Yes. The agent calls search_sequences to find routes in an area, then uses get_sequence to retrieve the chronological image list.

LangChain delegates execution to the MCP client, which manages connection pooling. You can add standard LangChain retry runnables to handle rate limits gracefully.

Use get_image and pass specific fields like geometry, compass angle, or thumbnail URLs. This limits the payload size to exactly what your agent needs.

The MCP server runs in an isolated V8 sandbox and never stores your API tokens, street-level imagery, GPS coordinates, or compass angles. It acts as a direct, stateless pass-through between LangChain and the Mapillary API.

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