How to Use the Bold MCP in Pydantic AI

Use Bold with Pydantic AI for type-safe Colombian payment processing and strict runtime validation of all merchant data actions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bold MCP to Pydantic AI

Create your Vinkius account to connect Bold 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 Bold with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe payments with Pydantic AI

Call `create_online_payment` knowing your inputs are validated. Pydantic AI checks your data against the required schema before the request hits the server. Retrieve details with `get_transaction` to ensure the response matches your expected model. If the data looks wrong, the agent stops immediately.

Hardware control in Pydantic AI

Query `list_terminals` to get an array of available devices. Your agent maps these to Pydantic objects for easy filtering and selection. Trigger payments with `initiate_terminal_payment` using validated terminal IDs. This prevents runtime errors during the payment sequence.

Track balances via Pydantic AI

Use `get_account_balance` to check your current funds. The server returns a structured response that your agent validates automatically. List recent history with `list_transactions` to reconcile your books. Pydantic AI ensures every record parses correctly into your objects.

Setup guide

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

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

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

The MCPToolset automatically validates every response against your Pydantic models. If the server returns unexpected fields, the agent raises a validation error instead of processing bad data.

Yes, it is model-agnostic. You configure the server via HTTP, and your agent uses the tools regardless of which LLM is running the logic.

It is. Because the server tools are exposed through the MCPToolset, every input and output is strictly checked against your defined models at runtime.

You do. The server only exposes the tools you allow, and all communication happens over a secure, authenticated channel managed by Vinkius.

The server acts as a thin interface for your agent. It pulls only the transaction and account data you request, keeping the rest of your merchant profile 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