Which countries are supported by the Fintoc MCP server?

Fintoc currently supports major financial institutions in Chile (cl) and Mexico (mx). You can use the 'list_institutions' tool to see the specific banks available in each region.

Can I filter bank movements by specific dates using the agent?

Yes! The 'list_movements' tool accepts 'since' and 'until' parameters in ISO format. For example, you can ask the agent to 'List movements from 2023-01-01 to 2023-01-31' for a specific account.

How secure is my bank data when using Fintoc through Vinkius?

Your security is paramount. Vinkius encrypts your Fintoc Secret Key at rest and only injects it into the isolated execution environment. Fintoc uses read-only access for movements and bank-grade security for all operations.

Fintoc MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Fintoc
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Fintoc through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Fintoc "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Fintoc?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About Fintoc MCP Server

Connect your Fintoc account to any AI agent and automate your open banking and payment operations through the Model Context Protocol (MCP). Fintoc is the leading API for financial integration in Latin America (Chile and Mexico), allowing you to securely access real-time bank data and programmatically initiate transfers.

Pydantic AI validates every Fintoc tool response against typed schemas, catching data inconsistencies at build time. Connect 12 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.

What you can do

Bank Connectivity — List and manage your active bank links to maintain persistent access to financial data.
Account Inspections — Fetch detailed information for all linked bank accounts, including available balances and holder details.
Movement History — Retrieve transaction history (movements) for any account with powerful filtering options by date.
Payment Initiation — Create and monitor payment intents to automate bank transfers directly through the agent.
Subscription Tracking — List and manage active subscriptions to keep track of recurring payments.
Institution Discovery — Discover supported banks and financial institutions across different countries (Chile and Mexico).
Real-time Monitoring — Fetch specific movement details or payment intent statuses to keep your financial operations in sync.

The Fintoc MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Fintoc to Pydantic AI via MCP

Follow these steps to integrate the Fintoc MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Fintoc with type-safe schemas

Why Use Pydantic AI with the Fintoc MCP Server

Pydantic AI provides unique advantages when paired with Fintoc through the Model Context Protocol.

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 Fintoc integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Fintoc connection logic from agent behavior for testable, maintainable code

Fintoc + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Fintoc MCP Server delivers measurable value.

Type-safe data pipelines: query Fintoc with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Fintoc tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Fintoc and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Fintoc responses and write comprehensive agent tests

Fintoc MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Fintoc to Pydantic AI via MCP:

create_payment_intent

Create a payment intent

get_account

Get account details

get_link

Get link details

get_movement

Get movement details

get_payment_intent

Get payment intent details

get_subscription

Get subscription details

list_accounts

List accounts for a link

list_institutions

List supported institutions

list_links

List all links

list_movements

List movements for an account

list_payment_intents

List payment intents

list_subscriptions

List subscriptions

Example Prompts for Fintoc in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Fintoc immediately.

"List all my bank accounts linked to Fintoc."

"Show me the last 5 transactions for account 'acc_9876'."

"Which banks are supported in Chile (cl)?"

Troubleshooting Fintoc MCP Server with Pydantic AI

Common issues when connecting Fintoc to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Fintoc + Pydantic AI FAQ

Common questions about integrating Fintoc MCP Server with Pydantic AI.

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 Fintoc MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.