How to Use the Belvo MCP in CrewAI

Q: How do I limit which Belvo MCP tools a CrewAI agent can use?

Use the MCPServerHTTP class from crewai.mcp and apply a toolfilter. This lets you restrict a specific agent to only read balances with listbalances while blocking write operations.

Deploy autonomous teams of financial agents using CrewAI and the Belvo MCP Server.

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 CrewAI

Create your Vinkius account to connect Belvo to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Credit Risk Assessment

Using the `list_accounts` tool, a research agent in your crew can fetch active bank accounts and share them with an analyst agent. Analyzing credit risk requires multiple viewpoints. With CrewAI, your agents share memory to build a complete profile without duplicating API requests. The team coordinates using sequential execution. Once the research agent verifies the account holder with `list_owners`, the analyst agent calculates the debt-to-income ratio using the fetched balances.

Autonomous Expense Auditing Teams

The `list_recurring_expenses` tool lets your monitoring agent track corporate spending across Latin America and flag unusual charges. Keeping track of corporate spending is a headache. By hooking this MCP Server into your crew, a monitoring agent can run checks and pass suspicious items to a moderator agent. You configure this by passing the Vinkius SSE or HTTP URL directly into the agent's `mcps` array. The agents handle the tool selection autonomously, calling `get_transaction` only when they need to drill down into a specific line item.

Multi-Agent Investment Tracking in CrewAI

Using the `get_investments` tool, your investment crew pulls real-time asset allocations from Mexican and Brazilian institutions. Managing diverse portfolios requires constant oversight. Your investment crew can use this tool over the MCP link to pull asset allocations from different institutions. This multi-agent setup ensures that data fetching and data formatting are handled by separate, specialized entities. Your main agent stays focused on decision-making while the helper agents fetch the raw financial records.

Setup guide

Set up Belvo MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Belvo tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Belvo Analyst",
    goal="Access and analyze Belvo data via MCP.",
    backstory="Expert analyst with direct Belvo access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Belvo transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

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

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Belvo Analyst",
        goal="Access and analyze Belvo data via MCP.",
        backstory="Expert analyst with direct Belvo access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Belvo transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

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

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 CrewAI

You can pass your Vinkius HTTP endpoint directly into the agent's `mcps` list during initialization. CrewAI automatically discovers the financial tools and exposes them to that specific agent.

Yes, agents in the same crew use shared memory to pass context. If one agent fetches transaction history using `list_transactions`, another agent can analyze that data without hitting the API again.

Use the `MCPServerHTTP` class from `crewai.mcp` and apply a `tool_filter`. This lets you restrict a specific agent to only read balances with `list_balances` while blocking write operations.

Yes, you can appoint a manager agent to oversee the financial analysis. The manager delegates tasks like calling `list_incomes` to subordinate agents and reviews the final financial report.

All transaction data and owner records retrieved from Latin American banks are processed transiently in memory. Vinkius isolates the runtime environment, meaning no financial records are ever written to disk or used for training models.

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