How to Use the Mercury MCP in Pydantic AI

Type-safe Mercury integration for Pydantic AI. Validate every banking response at runtime to ensure absolute data integrity.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mercury MCP to Pydantic AI

Create your Vinkius account to connect Mercury 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 Mercury with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Mercury data validation

Every response from `list_payments` or `list_statements` is forced through Pydantic models. If the data structure drifts, the agent halts immediately. This prevents the common issue of hallucinated fields. Your financial logic stays consistent and predictable.

Strict account management

Use `get_account` to verify details before triggering any payment logic. The framework ensures the data matches your defined schema perfectly. It's the safest way to interact with your treasury. If the API returns garbage, your agent rejects it before any action occurs.

Reliable recipient workflows

The `create_recipient` tool works under the same type-safety rules. You get clear validation errors if your inputs don't meet the bank's requirements. It removes the guesswork from agent-led operations. You define the model, and the MCP server satisfies it.

Setup guide

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

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

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

The framework matches every tool output against your defined models. Any deviation results in an immediate, loud validation error.

Yes, it supports both SSE and Streamable HTTP. You connect via the MCPToolset class for a unified integration.

The setup is model-agnostic. Whether you use OpenAI or a local model, the Pydantic schema validation keeps your data clean.

The agent will fail the validation step. This prevents corrupted data from ever reaching your core logic or internal systems.

Your data is handled within an ephemeral Vinkius sandbox. We ensure that only the specific transaction and recipient details you authorize are accessed.

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