Bring Card Issuing
to Pydantic AI
Learn how to connect Marqeta to Pydantic AI and start using 31 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Marqeta MCP Server?
Connect your Marqeta account to any AI agent to manage your card issuing infrastructure through natural conversation. This server provides comprehensive tools for managing the entire lifecycle of card programs.
What you can do
- User & Business Management — Create and retrieve individual users or business entities to act as account holders.
- Card Issuance — Create physical or virtual payment cards and manage card products that define spending behaviors.
- Funding & GPA Orders — Move funds into account holder General Purpose Accounts (GPA) and manage ACH funding sources.
- Inventory & Retrieval — List users, fetch specific card details, and audit all cards associated with a specific user token.
- Configuration — Define card products with specific start dates and names to control your issuing environment.
How it works
- Subscribe to this server
- Enter your Marqeta Application Token and Admin Access Token
- Provide your Base URL (Sandbox or Production)
- Start issuing cards and managing fintech workflows from your MCP-compatible client
Built-in capabilities (31)
Create an ACH funding source
Create an authorization control
Create a new Marqeta business
Create a new Marqeta card
Create a new Marqeta card product
g., ACTIVE, SUSPENDED, TERMINATED). Create a card transition
g., to reverse a deposit). Create a direct deposit transition
Create a GPA order to fund an account
Create a payment card funding source
Create a PIN control token
Create a program funding source
Create a new Marqeta user
g., ACTIVE, SUSPENDED, CLOSED). Create a user transition
Create a velocity control
Create a webhook
Retrieve balances for a user or business
Retrieve a Marqeta business by token
Retrieve a Marqeta card by token
Retrieve a direct deposit record
Retrieve a Marqeta user by token
List all cards for a specific user
List Marqeta users
Perform KYC verification for a user
Ping a webhook
Provision a card for Apple Pay
Provision a card for Google Pay
Reveal a card PIN
Simulate an authorization
Simulate a clearing transaction
Simulate a reversal
Set or update a card PIN
Why Pydantic AI?
Pydantic AI validates every Marqeta tool response against typed schemas, catching data inconsistencies at build time. Connect 31 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Marqeta integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Marqeta connection logic from agent behavior for testable, maintainable code
Marqeta in Pydantic AI
Marqeta and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Marqeta to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Marqeta in Pydantic AI
The Marqeta MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 31 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Marqeta for Pydantic AI
Every tool call from Pydantic AI to the Marqeta MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I see all cards belonging to a specific person?
Use the list_cards_by_user tool by providing the user's unique token. The agent will return a list of all physical and virtual cards associated with that account holder.
How do I add money to a user's card account?
You can use the create_gpa_order tool. You'll need the user token, the amount, currency code, and a funding source token to move funds into their General Purpose Account.
Is it possible to register a legal entity instead of an individual?
Yes, use the create_business tool to create a business entity. You can then retrieve its details using the get_business tool with the business token.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Marqeta MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
ScraperAPI
10 toolsEquip your AI agent with proxy rotation and headless browsers to extract HTML, Google SERPs, and Amazon data at scale.
CallRail
10 toolsManage call tracking via CallRail — track calls, manage leads, and monitor marketing attribution directly from any AI agent.
Airbyte
7 toolsMonitor your Airbyte data pipelines via AI — track sync jobs, list sources, and check connections instantly.
Katalon TestOps (AI Test Management)
10 toolsManage test orchestration via Katalon TestOps — rerun test runs, monitor execution results, and audit software releases.