How to Use the Jawg Maps (Location & Routing) MCP in Pydantic AI

Q: Does Pydantic AI support the deprecated HTTP transport for this server?

No, you should use the unified MCPToolset with the Vinkius HTTP endpoint. This handles connection pooling and tool registration natively, avoiding the setup issues associated with deprecated connection methods.

Bring strict type safety to routing and location search with 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 Jawg Maps (Location & Routing) MCP to Pydantic AI

Create your Vinkius account to connect Jawg Maps (Location & Routing) 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 Jawg Maps (Location & Routing) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe address validation in Pydantic AI

This MCP Server provides `search_map_places` and `search_autocomplete` to return raw location data that Pydantic AI validates against strict Python schemas at runtime. If the mapping API returns unexpected fields, the framework raises a validation error immediately instead of letting your agent hallucinate coordinates. You can also use `search_country_filter` to enforce country boundaries. Pydantic AI guarantees that the resulting coordinates strictly match your application's internal data models before your business logic ever touches them.

Validated routing paths via this MCP Server

`calculate_routing_line` and `calculate_distance_matrix` provide complex nested lists of coordinates and durations that are prone to parsing errors. Pydantic AI parses these outputs directly into structured Python objects, ensuring your routing logic never crashes due to a null value. This type-safe structure makes it easy to pass route data safely to downstream services. Your agent can confidently extract distance values, knowing the types are validated at the API boundary.

Validated terrain profiles for Pydantic AI

`calculate_elevation_routing` and `get_path_elevation` return vertical profiles that require precise decimal parsing. Pydantic AI validates these elevation arrays, ensuring your application gets actual floating-point numbers rather than messy strings. Similarly, when calculating delivery boundaries, `calculate_distance_isochrone` outputs polygon coordinates that represent reachable areas. Pydantic AI ensures these polygons are formatted correctly before you attempt to render them on a frontend map.

Setup guide

Set up Jawg Maps (Location & Routing) 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": {
        "jawg-maps-location-routing-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Jawg Maps (Location & Routing) 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 Jawg Maps. 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 Jawg Maps (Location & Routing) 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 Jawg Maps (Location & Routing) MCP in Pydantic AI

The framework wraps this MCP Server tools in dynamic Pydantic models. When a tool like `calculate_routing_line` returns route coordinates, the data must pass type validation before the agent can access it.

Pydantic AI will fail loudly and raise a ValidationError. This prevents your agent from executing downstream actions with broken or corrupted coordinate data, keeping your production database clean.

No, you should use the unified `MCPToolset` with the Vinkius HTTP endpoint. This handles connection pooling and tool registration natively, avoiding the setup issues associated with deprecated connection methods.

Yes, Pydantic AI is model-agnostic. You can connect a local model or any major cloud provider to this server, and the framework will still enforce strict runtime validation on tools like `reverse_geocode`.

Your coordinates, search terms, and route polygons are processed in memory and validated locally by Pydantic AI. The underlying connection to the Vinkius sandbox uses secure TLS, and no location history is ever written to persistent storage.

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