How to Use the Bolt MCP in Pydantic AI

Run type-safe checkout operations with Pydantic AI and the Bolt MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bolt MCP to Pydantic AI

Create your Vinkius account to connect Bolt 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 Bolt with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Bolt order structures at runtime

The `get_order_details` tool fetches raw purchase data that Pydantic AI immediately validates against strict schema types. If the API returns unexpected fields, the framework raises a validation error instead of letting your agent hallucinate. This strict type checking guarantees that your agent receives clean, predictable structures when managing orders. You don't have to write manual parsing code for customer checkout tokens.

Process refunds safely using Pydantic AI MCP Server

The `refund_transaction` tool processes money returns with runtime type guarantees. Your Pydantic AI agent validates the refund amount and transaction ID before the tool payload ever leaves your application. By using the unified MCPToolset, your agent discovers these tools and maps their inputs to Pydantic models. This setup prevents malformed payloads from reaching Bolt, protecting your merchant account from API errors.

Audit checkout setups with type-safe tools

The `get_account_details` tool retrieves your merchant profile to verify your active checkout configuration. Your Pydantic AI agent parses the returned account metadata to ensure your store settings match your local environment variables. You can pair this with `list_webhooks` to verify that your transaction listeners are active. Pydantic AI's model-agnostic engine handles these checks whether you run your agent on local models or commercial APIs.

Setup guide

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

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

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

Install pydantic-ai-slim with the mcp extra. Instantiate MCPToolset pointing to your Vinkius HTTP endpoint, and pass it to your Agent constructor.

Yes, the framework generates Pydantic schemas from the tool definitions. If your agent tries to call `void_transaction` with an invalid ID format, the SDK blocks the call before execution.

Wrap your agent runs in standard Python try-except blocks. If tools like `capture_transaction` fail, the framework raises a clean validation or execution error you can handle programmatically.

No, that class is deprecated. You should use the unified MCPToolset class to connect your agent to the Vinkius-hosted MCP endpoint.

Vinkius isolates the server in an ephemeral sandbox, securing your merchant status and transaction records. Your API keys are injected at the sandbox level, keeping them out of your agent's prompts and logs.

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