How to Use the Mapillary MCP in Pydantic AI

Q: How do I set up the Mapillary MCP Server with Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your HTTP endpoint URL. Pass it directly to your Agent via the toolsets parameter.

Q: Does Pydantic AI validate Mapillary API responses?

Yes. Every time your agent calls getimage or getsequence, the framework checks the returning JSON against strict runtime models. Bad data triggers an immediate error.

Q: What happens if the Mapillary MCP Server returns unexpected data to Pydantic AI?

The agent fails loudly. If getimagedetections returns a string instead of a float for a confidence score, you get a validation exception. No silent corruption.

Type-safe street-level imagery mapping for Pydantic AI agents.

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 Pydantic AI

Create your Vinkius account to connect Mapillary to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect the Mapillary MCP Server with absolute type safety

Pydantic AI refuses to tolerate silent failures. When you connect this MCP server using the `MCPToolset` class, every single API response gets validated against strict Pydantic models at runtime. If the API changes a field, your agent fails loudly instead of hallucinating data. Your agent calls `search_images` with a specific bounding box. The server returns image IDs, coordinates, and capture dates. The framework verifies that every latitude and longitude is an actual float before the model even sees the `get_image` response. You get guaranteed correctness.

Validate traffic sign detections instantly

Road object data is useless if the schema is broken. Your agent runs `get_map_features` to pull traffic sign types and GPS coordinates. Pydantic AI ensures the confidence scores are actual numbers, not strings or nulls, before your application logic touches them. When the agent needs specifics, it hits `get_image_detections`. It extracts the exact geometry and detection values from the photo. Because the framework is model-agnostic, you can swap between Anthropic and local models without changing how the tool validates the incoming metadata.

Audit image sequences without silent corruption

Mapping contiguous routes requires exact sequence IDs. The agent uses `search_sequences` to find paths through an area, then feeds those IDs into `get_sequence`. If the API drops the creation date field, Pydantic AI throws a validation error immediately. You can then run `get_detection_value` on specific objects found along that route. Your agent builds a completely verified inventory of street-level infrastructure, and you never have to worry about a missing compass angle crashing your downstream pipeline.

Setup guide

Set up Mapillary MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "mapillary-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Mapillary tools.",
)

result = await agent.run("List recent Mapillary transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your HTTP endpoint URL. Pass it directly to your Agent via the `toolsets` parameter.

Yes. Every time your agent calls `get_image` or `get_sequence`, the framework checks the returning JSON against strict runtime models. Bad data triggers an immediate error.

Any model the framework supports. You can use OpenAI, Anthropic, or local models to run `search_images` and `get_map_features`. The toolset handles the translation layer.

The agent fails loudly. If `get_image_detections` returns a string instead of a float for a confidence score, you get a validation exception. No silent corruption.

The tool handles geographic bounds, image IDs, and object detection types. Vinkius hosts this as an ephemeral instance where no logs or queries are written to disk. The execution environment self-destructs the moment your agent finishes parsing the response.

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