How to Use the Marqeta MCP in Pydantic AI

Q: How do I attach the Marqeta MCP Server to Pydantic AI?

Use the unified MCPToolset class with your Vinkius HTTP endpoint. Pass this toolset directly into the toolsets parameter of your Agent instance.

Q: Does Pydantic AI validate Marqeta webhook setups?

Yes. When the agent uses createwebhook or pingwebhook, Pydantic AI checks the structure of the returned payload. If the webhook URL format is invalid, it throws a validation error immediately.

Q: Can my Pydantic AI agent provision cards for digital wallets via Marqeta?

It can manage the process. The agent calls provisionapplepay or provisiongooglepay and validates the resulting cryptographic payload before passing it back to your mobile client.

Connect Marqeta to Pydantic AI to issue cards and validate every single payment payload at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marqeta MCP to Pydantic AI

Create your Vinkius account to connect Marqeta 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 Marqeta with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Marqeta MCP Server

Financial APIs cannot tolerate silent failures. When your agent calls this MCP Server for `create_user` or `create_card`, Pydantic AI validates the response against strict schemas. If the API returns a missing user token, the agent fails loudly instead of hallucinating a fake string. This exactness matters when moving money. You want absolute certainty before calling `create_ach_funding_source` or `create_gpa_order`. The framework guarantees that the inputs match the required types before the network request even fires.

Manage Authorizations and Reversals

Simulating payment flows requires complex nested JSON. Your agent can trigger `simulate_authorization` to test a swipe, followed by `simulate_reversal` to test a refund. Pydantic catches any malformed ISO 8583 fields immediately. You can also manage real card states. The agent can execute `create_card_transition` to freeze an account. Because it is model-agnostic, you can swap out OpenAI for Anthropic and the validation logic remains identical.

Enforce Velocity and PIN Controls

Setting up spend limits requires precision. The agent uses `create_velocity_control` and `create_auth_control` to restrict daily spend. If the agent tries to pass a string instead of an integer for the limit, Pydantic blocks it. PIN management works the same way. The agent handles `create_pin_control_token` and `update_pin` securely. It reads `get_balances` to verify the account is active before allowing any PIN resets.

Setup guide

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

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

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

Use the unified `MCPToolset` class with your Vinkius HTTP endpoint. Pass this toolset directly into the `toolsets` parameter of your Agent instance.

Yes. When the agent uses `create_webhook` or `ping_webhook`, Pydantic AI checks the structure of the returned payload. If the webhook URL format is invalid, it throws a validation error immediately.

It can manage the process. The agent calls `provision_apple_pay` or `provision_google_pay` and validates the resulting cryptographic payload before passing it back to your mobile client.

Any model supported by the framework. You can use Gemini, Claude, or local models to trigger `perform_kyc` and `create_business`. The type validation sits between the model and the API.

This server processes raw KYC documents and unmasked card balances. The zero-trust Vinkius architecture ensures that your Pydantic schemas only validate data in memory, dropping the connection and destroying the sandbox the millisecond the request completes.

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