How to Use the Mercury MCP in Pydantic AI

Q: How do I install the Mercury toolset for Pydantic AI?

Install the package using pip install "pydantic-ai-slimmcp" and initialize MCPToolset with your Vinkius URL. Pass this toolset to your Pydantic AI agent's toolsets parameter to enable Mercury banking tools.

Q: Does this integration support sending money?

No, this MCP Server only exposes read tools like listtransactions, listinvoices, and getbalance. Your money remains completely safe because the Pydantic AI agent has no write access to transfer Mercury funds.

Validate Mercury transactions and balances at runtime with type-safe Pydantic AI agents.

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 Balance Checks with Pydantic AI

The `get_balance` tool retrieves your current Mercury startup bank balance with strict runtime validation. Pydantic AI guarantees that the numeric values returned match your exact Python schema before your agent can use them. If the Mercury API returns unexpected data, the Pydantic AI framework fails loudly with a validation error. This prevents your agent from making critical financial decisions based on corrupted or hallucinated balance figures.

Validated Invoice Audits via MCP Server

The `list_invoices` tool pulls active Mercury receivable records directly into your type-safe agent. Pydantic AI parses the incoming JSON payload against structured models to ensure every invoice field is clean. You connect this by initializing `MCPToolset` with your Vinkius HTTP URL and passing it to the Pydantic AI agent's `toolsets` parameter. The unified toolset approach ensures smooth compatibility with any LLM backend you choose to analyze Mercury data.

Clean Recipient Verification

The `list_recipients` tool exposes your Mercury payment recipient list to your verification agents. Your Pydantic AI agent checks this list to ensure payment targets are valid before you queue up manual wires. By using this MCP Server, you bypass writing custom validation logic for the Mercury banking API. The Pydantic AI framework handles the parsing, so your agent only acts on verified, structured recipient profiles.

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-alternative-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

Install the package using `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` with your Vinkius URL. Pass this toolset to your Pydantic AI agent's `toolsets` parameter to enable Mercury banking tools.

The framework intercepts the response and validates it against strict schemas for Mercury tools like `list_transactions`. If there is a schema mismatch, Pydantic AI raises a validation error instead of passing bad data to your agent.

Yes, Pydantic AI is model-agnostic. You can run local models or any major cloud LLM to analyze your Mercury `list_cards` or `list_recipients` data, as long as the models support tool calling.

No, this MCP Server only exposes read tools like `list_transactions`, `list_invoices`, and `get_balance`. Your money remains completely safe because the Pydantic AI agent has no write access to transfer Mercury funds.

Your Mercury bank account details, balances, invoices, and transaction histories flow directly through an ephemeral, zero-trust MCP Server environment on Vinkius. The data is processed strictly in-memory and immediately destroyed post-execution, keeping your banking credentials completely isolated from Pydantic AI and LLM providers.

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