How to Use the Pelias Geocoder MCP in Pydantic AI

Q: How do I restrict searches to specific types of places, like venues or cities?

Your agent can call searchlayerfilter to limit the query to specific layers. This keeps the returned dataset clean and prevents the model from getting confused by overlapping geographic boundaries.

Validate every address and coordinate with Pydantic AI and the Pelias Geocoder MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pelias Geocoder MCP to Pydantic AI

Create your Vinkius account to connect Pelias Geocoder to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pelias Geocoder with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Ensure type-safe geocoding in Pydantic AI.

When your agent parses spatial data, a single malformed coordinate can break your entire backend. This MCP Server integrates with Pydantic AI to validate every geocoding response against strict Python types before your code ever runs. By calling `search_geocode` or `reverse_geocode`, the agent receives structured JSON that is immediately validated. If Pelias returns unexpected fields or missing data, Pydantic AI raises a validation error immediately, preventing corrupt coordinate data from entering your database.

Run bulletproof address normalization.

Messy user-submitted addresses are a nightmare for automation. This setup uses `structured_geocoding` to split raw input strings into clean, structured fields like street, city, and region, validating the output at runtime. Your agent can then use `search_autocomplete` to suggest corrections as users type. Because Pydantic AI enforces strict schemas, you can guarantee that the suggested addresses match the exact shape your database expects, eliminating silent parsing failures.

Constrain spatial queries with runtime validation.

Prevent your model from hallucinating coordinates outside your business boundaries. By using `search_bounding_box` and `search_country_filter`, you restrict the valid search area to specific geographic coordinates and ISO codes. Pydantic AI ensures that the bounding box parameters passed to the tool match your exact float and array schemas. The agent uses `search_focus_bias` to prioritize nearby results, keeping the search context tight and the data strictly validated.

Setup guide

Set up Pelias Geocoder 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": {
        "pelias-geocoder-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Initialize the MCPToolset with your Vinkius HTTP endpoint. Then, pass this toolset directly into the toolsets argument when defining your Agent instance to make tools like structured_geocoding available to your model.

Pydantic AI will raise a validation error at runtime. This prevents your agent from passing bad coordinates to functions like reverse_distance_limit and ensures that only perfectly structured spatial data is processed.

Yes, Pydantic AI is model-agnostic. You can connect this MCP Server to local models running via Ollama or enterprise models like Claude, and they will all use the exact same validated geocoding tools.

Your agent can call search_layer_filter to limit the query to specific layers. This keeps the returned dataset clean and prevents the model from getting confused by overlapping geographic boundaries.

All geospatial coordinates and address strings are processed in zero-trust, ephemeral V8 isolates. No data is stored or logged permanently, ensuring your users' private location queries remain completely confidential.

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