How to Use the CVM Dados Abertos MCP in CrewAI

Q: How can I assign CVM Dados Abertos tools to a specific agent in my CrewAI project?

When you configure the MCP server connection, use the toolfilter parameter. This lets you expose specific tools, like searchdatasets, to only the agents that need them.

Q: What's the easiest way to connect my CrewAI project to the CVM Dados Abertos MCP server?

Just pass your Vinkius endpoint URL directly into the mcps list when you define your agent. CrewAI handles the connection and makes the tools available automatically.

Q: Can my CrewAI agents discover what data is available on their own?

They can. The listdatasets and listgroups tools are made for this. You can create an exploratory agent whose job is to map out the data landscape before other agents act on it.

Equip your CrewAI agents with Brazilian market data expertise. Build autonomous teams to research and analyze CVM data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CVM Dados Abertos MCP to CrewAI

Create your Vinkius account to connect CVM Dados Abertos 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 CVM Dados Abertos with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy a CVM Research Specialist Agent

Create an agent in your crew with one job: CVM Data Researcher. Give it access to this MCP server's `search_datasets` and `list_datasets` tools. You can task this agent to find all documents related to a specific company, and it will autonomously query the CVM portal. The agent then passes its findings—a list of dataset IDs—to the next agent in the crew. The rest of your team doesn't need to know how the CVM portal works; they just get clean data to work with.

Autonomous Due Diligence Crews

Build a two-agent crew for market analysis. The first agent, a "Scout," uses `list_groups` and `list_datasets` to map out available data in a specific sector. It hands a summary off to the "Analyst" agent. The Analyst takes the Scout's list, uses `get_dataset` and `get_resource` to dig into the details, and synthesizes a report. CrewAI's shared memory lets them work together without you managing every step. This MCP provides the ground truth data for their entire operation.

Build a Market Watchdog Crew with this MCP Server

Set up a sequential crew that runs on a schedule. A "Watcher" agent uses `search_datasets` with a date filter to check for new company filings on the CVM portal. If it finds anything new, it passes the dataset IDs to a "Reporter" agent. The Reporter then uses `get_dataset` to pull the metadata and writes a summary for your team's Slack channel. It's a completely hands-off way to stay on top of market changes.

Setup guide

Set up CVM Dados Abertos 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 CVM Dados Abertos tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent CVM Dados Abertos 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="CVM Dados Abertos Analyst",
        goal="Access and analyze CVM Dados Abertos data via MCP.",
        backstory="Expert analyst with direct CVM Dados Abertos access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent CVM Dados Abertos 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 CVM Dados Abertos. 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 CVM Dados Abertos 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 CVM Dados Abertos MCP in CrewAI

When you configure the MCP server connection, use the `tool_filter` parameter. This lets you expose specific tools, like `search_datasets`, to only the agents that need them.

Yes, that's a perfect use case for CrewAI. Create a 'Researcher' agent with access to this MCP and a separate 'Analyst' agent. Set up a sequential task where the Researcher's output becomes the Analyst's input.

Just pass your Vinkius endpoint URL directly into the `mcps` list when you define your agent. CrewAI handles the connection and makes the tools available automatically.

They can. The `list_datasets` and `list_groups` tools are made for this. You can create an exploratory agent whose job is to map out the data landscape before other agents act on it.

Your agents only interact with public Brazilian capital markets data. Every tool call from your crew is routed through a private, single-use Vinkius sandbox, isolating your operations and ensuring no data leaks between sessions.

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