How to Use the IndoorAtlas (Indoor Positioning) MCP in Pydantic AI

Q: What happens if a Wi-Fi scan returns invalid data to Pydantic AI?

If positionfromwifiscan returns data that violates your Pydantic model, the framework raises a validation error. This prevents your agent from processing corrupt or incomplete location fixes.

Q: Can I validate GeoJSON floorplan files using the IndoorAtlas (Indoor Positioning) MCP Server in Pydantic AI?

Yes. When you use uploadfloorplangeojson, the server validates the GeoJSON structure. Pydantic AI ensures the response matches your expected floorplan schema before proceeding.

Q: How does my agent track the status of a radio map generation?

The agent calls listfloorplans and checks the readiness flag. Because Pydantic AI validates the boolean field, your agent can safely run conditional logic based on whether the map is ready.

Build type-safe indoor positioning pipelines that validate every coordinate and floor plan using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IndoorAtlas (Indoor Positioning) MCP to Pydantic AI

Create your Vinkius account to connect IndoorAtlas (Indoor Positioning) 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 IndoorAtlas (Indoor Positioning) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate spatial coordinates at runtime

The `position_from_wifi_scan` tool returns estimated coordinates and floor levels, which Pydantic AI immediately validates against strict runtime schemas. If the positioning API returns an unexpected coordinate format, the framework triggers an instant validation error. This strict validation prevents corrupt location data from entering your tracking databases. Your agent can confidently process these checked coordinates, knowing they match your exact Pydantic models.

Audit venue metadata with type safety

The `get_venue_details` tool retrieves the geographic anchor, floor count, and mapped area for any building in your account. Pydantic AI parses this metadata, ensuring the floor counts and coordinates match your application's data types. If you need to check multiple buildings, the agent calls `list_venues` to get a structured array of active properties. The framework ensures every venue object contains valid geographic coordinates before your agent acts on them.

Manage floorplans with this MCP Server

The `list_floorplans` tool returns details on dimensions and map readiness, which are validated against your schema. If a floorplan lacks a valid ID or scale, the framework halts the execution immediately. To fix missing layouts, the agent uses `upload_floorplan_geojson` to upload geo-referenced maps. Once uploaded, the agent calls `trigger_map_generation` to start the calibration process, ensuring the output matches your expected model.

Setup guide

Set up IndoorAtlas (Indoor Positioning) 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": {
        "indooratlas-indoor-positioning-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent IndoorAtlas (Indoor Positioning) 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 IndoorAtlas. 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 IndoorAtlas (Indoor Positioning) 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 IndoorAtlas (Indoor Positioning) MCP in Pydantic AI

Initialize the MCPToolset with your Vinkius HTTP endpoint. Pass this toolset directly into your Agent constructor to give your type-safe agent immediate access to all ten positioning tools.

If `position_from_wifi_scan` returns data that violates your Pydantic model, the framework raises a validation error. This prevents your agent from processing corrupt or incomplete location fixes.

Yes. When you use `upload_floorplan_geojson`, the server validates the GeoJSON structure. Pydantic AI ensures the response matches your expected floorplan schema before proceeding.

The agent calls `list_floorplans` and checks the readiness flag. Because Pydantic AI validates the boolean field, your agent can safely run conditional logic based on whether the map is ready.

All uploaded GeoJSON floorplan files are encrypted in transit and processed within an ephemeral sandbox. Vinkius never stores your map layouts or floor geometries permanently.

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