How to Use the Moneypenny MCP in Pydantic AI

Q: How do I register the Moneypenny MCP Server in Pydantic AI?

Use the MCPToolset class with your server URL to initialize the connection. Pass this toolset directly into your agent's toolsets argument to expose commands like getthisweekcalls.

Q: Is the deprecated MCPServerHTTP class still used here?

No, you should use the unified MCPToolset approach. This ensures your connection to tools like gettodaychats remains stable and uses the latest SDK standards.

Q: How does this MCP Server keep my customer phone messages secure?

All phone messages and chat transcripts retrieved by listcallmessages are validated in memory and passed directly to your agent. Vinkius's sandboxed environment ensures your API tokens never leak during validation.

Run type-safe customer communication pipelines using Pydantic AI to validate every Moneypenny call and chat transcript.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moneypenny MCP to Pydantic AI

Create your Vinkius account to connect Moneypenny 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 Moneypenny with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict runtime validation for call logs

If you need absolute certainty that your data matches your database schema, Pydantic AI is the tool. When your agent calls `get_today_calls`, the response is immediately validated against strict Python models at runtime. This prevents malformed receptionist data from corrupting your internal databases. If the API returns an unexpected date format, the system fails loudly instead of silently passing bad data down the line.

Reliable chat analysis using Pydantic AI

Your agent can safely query `get_recent_chats` to parse live chat transcripts. Because Pydantic AI validates the structure of every chat log, you can write clean code without worrying about missing fields. You can also use `list_chat_logs` to pull historical conversations for deep analysis. The framework ensures that timestamps and user IDs conform exactly to your defined types before your model processes them.

Type-safe status monitoring via MCP Server

Use this MCP Server to check your API connection status with `check_moneypenny_status` before executing complex workflows. Pydantic AI ensures the status response matches your exact boolean expectation. When pulling broader trends, your agent can run `get_activity_summary` to get a structured overview of the day's operations. This keeps your monitoring dashboards accurate and free from type errors.

Setup guide

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

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

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

Use the `MCPToolset` class with your server URL to initialize the connection. Pass this toolset directly into your agent's `toolsets` argument to expose commands like `get_this_week_calls`.

The framework raises a validation error immediately. This prevents your model from hallucinating information based on missing fields in tools like `list_call_messages`.

Yes, the toolset is completely model-agnostic. You can run your type-safe agent on local models or commercial APIs while pulling data from `get_this_week_chats`.

No, you should use the unified `MCPToolset` approach. This ensures your connection to tools like `get_today_chats` remains stable and uses the latest SDK standards.

All phone messages and chat transcripts retrieved by `list_call_messages` are validated in memory and passed directly to your agent. Vinkius's sandboxed environment ensures your API tokens never leak during validation.

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