How to Use the Belvo MCP in Pydantic AI

Q: How do I initialize the Belvo MCP Server in Pydantic AI?

Install the pydantic-ai-slimmcp package and create an MCPToolset with your HTTP endpoint. Pass this toolset to your agent to expose the financial tools.

Type-safe LATAM financial data extraction for 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 Belvo MCP to Pydantic AI

Create your Vinkius account to connect Belvo 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 Belvo with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Belvo MCP Server responses.

`list_institutions` and `list_links` return the available banks and active connections for a user. Pydantic AI checks every field in these responses against your predefined schemas at runtime. If the API changes a field name or returns an unexpected data type, the framework throws a validation error immediately. Your agent stops execution instead of silently passing corrupted data downstream.

Enforce strict schemas on incomes.

`list_incomes` and `list_recurring_expenses` pull structured cash flow analysis from the banking provider via MCP. You define the exact shape of this data using standard Python classes. The framework guarantees that the agent only receives data matching your schema. You never have to write custom parsing logic to handle missing fields or hallucinated keys.

Extract precise transaction records.

`list_transactions` and `get_transaction` fetch individual ledger entries from connected accounts. Your type-safe agent processes these records to build reliable accounting ledgers. Because Pydantic AI is model-agnostic, you can swap between local models and commercial APIs without changing your tool definitions. The validation layer remains identical regardless of the underlying LLM.

Setup guide

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

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

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

Install the `pydantic-ai-slim[mcp]` package and create an `MCPToolset` with your HTTP endpoint. Pass this toolset to your agent to expose the financial tools.

Financial APIs often return complex nested JSON that breaks agent logic. This framework validates the output of `get_account` before your agent ever sees it, preventing silent failures.

The framework supports both Streamable HTTP and SSE transports for tool execution. You configure the connection method when initializing the toolset.

The framework fails loudly with a validation error. Your agent will not attempt to process a `list_balances` response that is missing required fields.

This system handles raw bank balances and account ownership records. Vinkius runs the integration in an isolated sandbox that spins down immediately after the API call finishes, leaving no residual data.

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