How to Use the Google Contacts MCP in Pydantic AI

Q: How do I connect the Google Contacts tools to a Pydantic AI agent?

You initialize MCPToolset with the HTTP endpoint URL and pass it to your agent's toolsets parameter. This registers all 9 tools from the MCP Server and automatically infers their input and output validation schemas.

Q: How do I safely delete a contact using Pydantic AI and Google Contacts?

You call deletecontact by passing the exact contact resource name validated by your schema. We recommend wrapping this action in a confirmation step to ensure the agent does not delete contacts accidentally.

Build type-safe Google Contacts workflows with Pydantic AI to guarantee runtime validation on every address book update.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Contacts MCP to Pydantic AI

Create your Vinkius account to connect Google Contacts 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 Google Contacts with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe contact creation with Pydantic AI

`create_contact` and `update_contact` execute with full runtime schema enforcement to ensure your address book never receives malformed data. If your agent tries to write an invalid email format or a missing phone number, the system blocks the write. This strict validation prevents silent data corruption across your entire contact list. Pydantic AI raises immediate validation errors at the boundary, forcing your agent to correct the payload before sending it to Google.

Validated search and read schemas

`search_contacts` and `get_contact` return structured data mapped directly to Pydantic models. Your agent can confidently parse phone numbers, company names, and email addresses knowing the types are guaranteed at runtime. This type safety eliminates the common parsing bugs found in loose JSON integrations. You write clean, typed Python code that handles contact data without constant isinstance checks or defensive null handling.

Group list verification via the MCP Server

`list_contact_groups` and `get_contact_group` provide clean, structured labels for organizing your directory. Your agent reads these groups to determine mailing segments, with every group ID validated against your schema. If the Google API schema changes, your application fails loudly and immediately instead of propagating bad data. This structural guarantee is essential for production systems where contact categorization drives automated campaigns.

Setup guide

Set up Google Contacts 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": {
        "google-contacts-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You initialize `MCPToolset` with the HTTP endpoint URL and pass it to your agent's `toolsets` parameter. This registers all 9 tools from the MCP Server and automatically infers their input and output validation schemas.

The framework will raise a validation error immediately at the runtime boundary. This prevents your agent from parsing corrupted dictionary keys or hallucinating contact fields that do not exist.

Yes, you can connect using either Streamable HTTP or Server-Sent Events (SSE) transports. The MCP connection class handles the underlying network protocol while keeping your validation logic identical.

You call `delete_contact` by passing the exact contact resource name validated by your schema. We recommend wrapping this action in a confirmation step to ensure the agent does not delete contacts accidentally.

This MCP Server processes your raw address book payloads entirely in an ephemeral sandbox without local logging or storage. Vinkius secures the transport layer with token-based authentication, keeping your personal contact details isolated.

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