How to Use the Mapillary MCP in OpenAI Agents SDK

Q: How do I connect the Mapillary MCP Server to the OpenAI Agents SDK?

Install openai-agents via pip. Initialize MCPServerStreamableHttp with your Mapillary endpoint and pass it to your Agent constructor. The SDK auto-discovers all seven imagery tools immediately.

Q: Can my agent find specific traffic signs using Mapillary and OpenAI Agents SDK?

Yes. Your agent will call getmapfeatures to search an area for recognized objects. It returns the GPS coordinates and confidence scores for things like speed limit signs and crosswalks.

Build production-ready street-level imagery agents with OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Mapillary to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect the Mapillary MCP Server to your production agents

OpenAI Agents SDK hands you the tools to build systems that actually work in the real world. You drop this MCP server into your agent's context, and it instantly knows how to pull street-level imagery. Set `cacheToolsList=True` and your agent won't waste time re-discovering the API on every run. Your agent uses `search_images` to find photos inside a specific bounding box. When it needs the exact metadata, it calls `get_image` to pull coordinates, compass angles, and thumbnail URLs. The built-in tracing lets you watch exactly how the model decides which coordinates to check next.

Map road infrastructure with built-in guardrails

Finding traffic signs shouldn't require a fleet of survey trucks. Your agent queries `get_map_features` to pull an inventory of detected road objects and their confidence scores. If the model tries to hallucinate a coordinate format, the SDK's guardrails catch it before the request ever hits the API. For deeper analysis, hand off the task to a specialized vision agent. It can run `get_image_detections` to extract specific traffic sign geometries from a single photo. You get a fully auditable trail of every detection value and confidence score in your OpenAI dashboard.

Trace entire image sequences automatically

Single images only tell part of the story. Your system can call `search_sequences` to find every mapped route passing through a target area. Once it finds a route, the agent uses `get_sequence` to pull the creation date and the exact order of related images. This is where handoffs shine. One agent maps the sequence IDs, then passes the list to a secondary agent that runs `get_detection_value` on specific objects along that route. You build a pipeline that maps miles of road without writing custom API wrappers.

Setup guide

Set up Mapillary MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Mapillary tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Mapillary tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Mapillary tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Mapillary Agent",
            instructions="You have access to Mapillary tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Initialize `MCPServerStreamableHttp` with your Mapillary endpoint and pass it to your Agent constructor. The SDK auto-discovers all seven imagery tools immediately.

Yes. Your agent will call `get_map_features` to search an area for recognized objects. It returns the GPS coordinates and confidence scores for things like speed limit signs and crosswalks.

The SDK's built-in guardrails intercept the request. If the bounding box format for `search_images` is malformed, the agent catches the error and corrects its own input before execution.

Check your OpenAI dashboard. The SDK natively traces every call to `get_sequence` or `get_image_detections`, showing you exactly what the model requested and what the API returned.

This integration only reads public street-level imagery, GPS coordinates, and traffic sign metadata. Vinkius runs the server in an ephemeral V8 Isolate sandbox, meaning your bounding box queries and sequence lookups vanish the second the connection drops. Zero data persistence.

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