Can I send SPEI transfers to any Mexican bank from my AI agent?

Yes! Use the `create_transfer` tool with the recipient's 18-digit CLABE number, the amount in MXN, and an optional concept description. Transfers are processed instantly during banking hours through Mexico's SPEI interbank system.

Can I see which purchases were made with meses sin intereses?

Yes. Use `list_credit_card_transactions` to see all your credit card charges. Each transaction includes its installment details — whether it was a single payment or spread across 3, 6, 12, or 18 months interest-free (meses sin intereses), along with the remaining installments.

How does the spending analytics feature work?

Use `get_spending_analytics` with a period (last_month, last_3_months, last_year). It returns your spending broken down by category (food, transport, entertainment, etc.), your top merchants, and comparison percentages against your previous period.

Nubank MX MCP Server for CrewAI 14 tools — connect in under 2 minutes

Name: Nubank MX
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 14 Tools Framework

Connect your CrewAI agents to Nubank MX through Vinkius, pass the Edge URL in the `mcps` parameter and every Nubank MX tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

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

from crewai import Agent, Task, Crew

agent = Agent(
    role="Nubank MX Specialist",
    goal="Help users interact with Nubank MX effectively",
    backstory=(
        "You are an expert at leveraging Nubank MX tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token. get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Nubank MX "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 14 available tools "
        "and what they can do."
    ),
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

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 Nubank MX MCP Server

Connect your Nubank Mexico account to any AI agent and take control of your personal banking through natural conversation.

When paired with CrewAI, Nubank MX becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Nubank MX tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.

What you can do

Account Overview — Check your Cuenta balance, CLABE number, and annual yield (rendimiento) on deposits in real-time
Transaction History — Browse and inspect debit card purchases, SPEI transfers, ATM withdrawals, and incoming deposits with full merchant details
Credit Card Management — View your credit limit, current balance, monthly statements, meses sin intereses purchases, and minimum payment due dates
SPEI Transfers — Send instant interbank transfers to any Mexican bank account using CLABE numbers, with concept descriptions and recipient tracking
Bill Payments — Pay CFE, Telmex, water, internet, and other Mexican utility services directly from your Cuenta balance
Spending Intelligence — Access AI-powered spending analytics by category, with monthly trends and top merchant insights

The Nubank MX MCP Server exposes 14 tools through the Vinkius. Connect it to CrewAI 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 Nubank MX to CrewAI via MCP

Follow these steps to integrate the Nubank MX MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py. CrewAI auto-discovers 14 tools from Nubank MX

Why Use CrewAI with the Nubank MX MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Nubank MX through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Nubank MX + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Nubank MX MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Nubank MX for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Nubank MX, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Nubank MX tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Nubank MX against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Nubank MX MCP Tools for CrewAI (14)

These 14 tools become available when you connect Nubank MX to CrewAI via MCP:

create_transfer

Transfers are processed in real-time during banking hours. Send a SPEI transfer

get_account_balance

Check your current account balance

get_account_info

Get your Nubank Mexico account profile

get_credit_card_info

Get your Nubank credit card details

get_credit_card_statement

Defaults to the current open statement if no month is specified. Get a credit card statement

get_investments

View your Cajitas investment portfolio

get_spending_analytics

), showing monthly trends, top merchants, and comparisons to previous periods. Use the period parameter for specific timeframes. Get spending analytics and insights

get_transaction

Get full details of a specific transaction

list_bills

List pending bills and service payments

list_credit_card_transactions

settled status. List recent credit card transactions

list_rewards

List your Nubank reward points and benefits

list_transactions

Use limit and offset for pagination through large histories. List recent account transactions

list_transfers

List outgoing transfers

pay_bill

If no amount is specified, the full outstanding amount is paid. Supports partial payments for eligible billers. Pay a bill or service

Example Prompts for Nubank MX in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Nubank MX immediately.

"How much do I have in my Nubank account right now?"

"Send $5,000 MXN via SPEI to CLABE 012180001234567890 with concept 'Renta abril'."

"Show me my spending breakdown for last month."

Troubleshooting Nubank MX MCP Server with CrewAI

Common issues when connecting Nubank MX to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Nubank MX + CrewAI FAQ

Common questions about integrating Nubank MX MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.