How to Use the Mapflow MCP in Pydantic AI

Q: How do I initialize Mapflow in Pydantic AI?

Import the MCPToolset from the Pydantic AI library and pass the Mapflow MCP server HTTP URL. This registers all seven geospatial tools as strongly-typed functions that your agent can safely call.

Q: What models can I use for feature extraction?

Call listmodels to fetch the active catalog of extraction networks. The server exposes specific models trained to detect building footprints, road networks, and agricultural vegetation boundaries.

Build type-safe geospatial extraction agents using Pydantic AI and the Mapflow MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapflow MCP to Pydantic AI

Create your Vinkius account to connect Mapflow 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 Mapflow with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe imagery processing with Pydantic AI

`create_processing` initiates a feature extraction run with strict runtime validation on your coordinate parameters. Pydantic AI enforces type safety on the input JSON, stopping malformed bounding boxes before they hit the API. This prevents wasted API credits on bad coordinates. Once the job runs, your agent monitors progress with `get_processing_status` and grabs the final GeoJSON payload using `get_processing_result`.

Mapflow MCP Server model discovery

`list_models` provides a validated list of neural network options for mapping roads, buildings, or vegetation. The agent parses this list against a strict schema, ensuring the model ID matches expected formats. This structural check eliminates silent failures during model selection. Your agent can safely decide which model fits the current task, keeping your spatial pipeline predictable and crash-resistant.

Structured workspace management

`create_project` establishes isolated workspaces to keep your spatial processing jobs clean. Your agent organizes these environments dynamically, validating each project name and metadata field at runtime. Keeping track of active pipelines is handled programmatically. The agent uses `list_projects` and `list_processings` to verify the state of every project, ensuring your data pipelines remain clean.

Setup guide

Set up Mapflow 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": {
        "mapflow-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Mapflow 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 Mapflow. 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 Mapflow 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 Mapflow MCP in Pydantic AI

Import the `MCPToolset` from the Pydantic AI library and pass the Mapflow MCP server HTTP URL. This registers all seven geospatial tools as strongly-typed functions that your agent can safely call.

The agent validates the structure of the GeoJSON returned by `get_processing_result` against internal schemas. If the API returns unexpected geometry fields, the validation engine catches it immediately.

Yes, the toolset integrates directly into Python's async event loop. Your agent can poll `get_processing_status` across multiple concurrent extraction jobs without blocking your main application thread.

Call `list_models` to fetch the active catalog of extraction networks. The server exposes specific models trained to detect building footprints, road networks, and agricultural vegetation boundaries.

The Mapflow MCP integration runs inside a zero-trust, ephemeral V8 sandbox. Your coordinates and spatial vectors are processed in memory and never written to persistent disk storage, ensuring your location data remains secure.

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