IndoorAtlas (Indoor Positioning) MCP Server for Pydantic AI 10 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect IndoorAtlas (Indoor Positioning) through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to IndoorAtlas (Indoor Positioning) "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in IndoorAtlas (Indoor Positioning)?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About IndoorAtlas (Indoor Positioning) MCP Server
Connect your IndoorAtlas account to any AI agent and take full control of your smart building infrastructure and indoor positioning services through natural conversation.
Pydantic AI validates every IndoorAtlas (Indoor Positioning) tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Venue Management — List all registered indoor venues and retrieve detailed metadata including geographic anchor points and floor counts directly from your agent
- Floorplan Orchestration — Upload new floor plans as GeoJSON and manage geo-referencing to real-world coordinates for accurate indoor positioning
- Map Generation — Trigger the radio map generation process to compute positioning models from signal fingerprint data and floor geometry
- Analytics & Sessions — Retrieve historical positioning sessions and trace data to analyze occupancy patterns, dwell times, and path optimization
- Wi-Fi Positioning — Determine indoor location from Wi-Fi scans using the Positioning API to receive estimated coordinates and floor levels
- Calibration Audit — Inspect fingerprinting walk paths to assess calibration coverage and identify areas needing additional signal mapping
The IndoorAtlas (Indoor Positioning) MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect IndoorAtlas (Indoor Positioning) to Pydantic AI via MCP
Follow these steps to integrate the IndoorAtlas (Indoor Positioning) MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 10 tools from IndoorAtlas (Indoor Positioning) with type-safe schemas
Why Use Pydantic AI with the IndoorAtlas (Indoor Positioning) MCP Server
Pydantic AI provides unique advantages when paired with IndoorAtlas (Indoor Positioning) through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your IndoorAtlas (Indoor Positioning) integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your IndoorAtlas (Indoor Positioning) connection logic from agent behavior for testable, maintainable code
IndoorAtlas (Indoor Positioning) + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the IndoorAtlas (Indoor Positioning) MCP Server delivers measurable value.
Type-safe data pipelines: query IndoorAtlas (Indoor Positioning) with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple IndoorAtlas (Indoor Positioning) tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query IndoorAtlas (Indoor Positioning) and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock IndoorAtlas (Indoor Positioning) responses and write comprehensive agent tests
IndoorAtlas (Indoor Positioning) MCP Tools for Pydantic AI (10)
These 10 tools become available when you connect IndoorAtlas (Indoor Positioning) to Pydantic AI via MCP:
create_venue
The venue serves as the top-level container for floor plans and positioning data. After creation, upload floor plan images and calibrate for positioning accuracy. Create a new indoor venue in the IndoorAtlas platform by specifying the building name, geographic coordinates of the entrance, and initial configuration parameters for indoor positioning deployment
get_fingerprint_paths
Returns GeoJSON LineString features representing calibration paths. Use to assess calibration coverage and identify areas of the floor that need additional fingerprinting for better positioning accuracy. Retrieve the fingerprinting walk paths recorded for a specific floor plan as GeoJSON, showing the routes surveyors walked while collecting Wi-Fi/BLE signal data for positioning calibration
get_session_data
Returns the complete position trace as a series of timestamped fixes. Use for path visualization, behavioral analysis, and positioning quality assessment. Large sessions may contain thousands of position fixes. Retrieve the full positioning trace data for a specific IndoorAtlas session, including timestamped coordinate fixes, floor transitions, accuracy metrics, and sensor readings throughout the session duration
get_venue_details
Returns the venue configuration including coordinate reference, building dimensions, and mapping completeness metrics. Use to inspect a venue before deploying positioning or wayfinding features. Retrieve detailed metadata for a specific IndoorAtlas venue including its geographic anchor point, floor count, total mapped area, calibration status, and associated floor plan identifiers
list_floorplans
Returns an array of floor plan metadata objects ordered by floor number. Each entry includes the plan dimensions, pixel-to-meter scale, and whether radio map generation has been completed. List all floor plans uploaded to a specific IndoorAtlas venue, returning floor plan IDs, floor numbers, dimensions, geo-alignment status, and map generation readiness for each level of the building
list_positioning_sessions
Returns a paginated list of positioning sessions. Each session represents a continuous period of indoor tracking by a single device. Use for occupancy analytics, dwell time analysis, and path optimization studies. List historical indoor positioning sessions recorded by IndoorAtlas, returning session IDs, start/end times, venue associations, and device information for analytics and path replay
list_venues
Returns an array of venue objects. Each venue represents a physical building that has been set up for indoor positioning. Use to discover available venues before requesting floor plans or positioning data. List all indoor venues registered in your IndoorAtlas organization, returning venue IDs, names, geographic coordinates, and configuration status for each mapped building or facility
position_from_wifi_scan
Returns estimated coordinates with uncertainty radius. Use for server-side positioning when mobile SDK integration is not feasible. Determine indoor position from a Wi-Fi access point scan using the IndoorAtlas Positioning API, submitting observed signal strengths to receive a calculated latitude, longitude, floor level, and accuracy estimate
trigger_map_generation
This is a critical step — positioning will not work on a floor until map generation completes successfully. The process is asynchronous and may take several minutes depending on floor plan complexity. Trigger the IndoorAtlas radio map generation process for a specific floor plan, initiating the server-side computation that creates the positioning model from fingerprint data and floor plan geometry
upload_floorplan_geojson
After upload, trigger map generation to enable positioning on this floor. Upload a new floor plan to an IndoorAtlas venue as a GeoJSON document, geo-referencing the indoor map image to real-world coordinates for accurate positioning overlay
Example Prompts for IndoorAtlas (Indoor Positioning) in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with IndoorAtlas (Indoor Positioning) immediately.
"List all indoor venues in my IndoorAtlas account"
"Check the calibration paths for the 3rd floor of the 'Retail Mall'"
"List the most recent positioning sessions recorded today"
Troubleshooting IndoorAtlas (Indoor Positioning) MCP Server with Pydantic AI
Common issues when connecting IndoorAtlas (Indoor Positioning) to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiIndoorAtlas (Indoor Positioning) + Pydantic AI FAQ
Common questions about integrating IndoorAtlas (Indoor Positioning) MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Connect IndoorAtlas (Indoor Positioning) with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect IndoorAtlas (Indoor Positioning) to Pydantic AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.