CVM Dados Abertos MCP for AI. Query Brazilian market data directly.

Q: How do I list all available data packages using listdatasets?

You call listdatasets with no arguments. This command returns a full inventory, showing you every dataset package on the CVM portal that your agent can access.

Q: Can I find filings for 'fundos' using searchdatasets?

Yes, use searchdatasets and pass 'fundos' as the query term. The system will return specific dataset names like 'fi-cad,' which you can then investigate further.

Q: What is the difference between getdataset and getresource?

getdataset gives you metadata about a whole collection (the container). getresource gets details about one specific file, like its download link or format.

Q: If I use getdataset, how do I actually get the download link for a CSV file?

You must run getresource after getting the metadata. The dataset tells you what data exists, but the resource tool retrieves the direct links and specific file details.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

CVM Dados Abertos gives you direct access to Brazil's capital markets data from the CVM Open Data portal. Your agent queries investment funds, listed companies, and financial reports without needing to navigate complex web directories or download files manually.

It lets you find specific regulatory filings, inspect dataset metadata, and map out which departments publish what kind of market information.

What your AI can do

List groups

Shows thematic groups, like 'Investment Funds,' that categorize financial market information.

List organizations

Lists the specific CVM departments responsible for publishing sets of data on the portal.

List datasets

Lists every available data package on the CVM portal so you can see all options.

+ 3 more capabilities included

Find all available datasets

The agent lists every dataset package available on the CVM portal so you can see what’s in scope.

Search for specific data topics

You can narrow down the massive catalog by searching keywords, like 'fundos' or 'companhias'.

Get detailed dataset metadata

The tool fetches complete details on a package, including its tags and ownership information.

Identify publishing organizations

List the specific CVM departments or groups responsible for creating certain sets of financial data.

Retrieve resource links

The agent gets direct metadata and download details (CSV, XML) for a specific file within a dataset.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

CVM Dados Abertos: 6 Tools for Financial Research

These six tools let you systematically explore the CVM Open Data portal. You can list all available data sets, search specific topics, and get deep metadata on both packages and individual files.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using CVM Dados Abertos on Vinkius

List Groups

Shows thematic groups, like 'Investment Funds,' that categorize financial market information.

List Organizations

Lists the specific CVM departments responsible for publishing sets of data on the...

List Datasets

Lists every available data package on the CVM portal so you can see all options.

Search Datasets

Searches across all available datasets using keywords to find matching topics or...

Get Dataset

Retrieves full metadata for one specific data package on the CVM portal.

Get Resource

Gets metadata and file details for a single, downloadable resource within a dataset.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The CVM Dados Abertos integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "cvm-dados-abertos": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the CVM Dados Abertos tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"cvm-dados-abertos": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with CVM Dados Abertos, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 6 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Navigating Brazilian financial data without a map is painful.

Right now, finding official market information means logging into multiple government portals. You click through category menus—'Investment Funds,' then 'Reports,' then you hit a folder with dozens of years and departments. You spend half your time just figuring out which link is the most current version or who published it.

With this MCP, you treat the entire CVM data portal like one single database. Your agent handles all that clicking for you. You simply ask what you need—say, 'Show me everything related to listed companies'—and get a structured list of sources.

Getting Metadata with `get_dataset` provides immediate context.

Before using the data from any specific dataset, you have to manually check its metadata. Is it updated daily or monthly? Which tags apply? You might miss critical details just by looking at a title.

Now, after identifying a package name, calling `get_dataset` instantly provides that full context. You know its update frequency and ownership right away. No guesswork required.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

This MCP connects your AI client directly to the Comissão de Valores Mobiliários (CVM) Open Data portal, letting you talk to Brazilian financial data like it’s a natural conversation. Instead of clicking through endless folders or hunting for specific CSV links, your agent handles the deep work. You can ask for all available datasets, check the metadata on any package—like its update frequency or who owns it—and even list which departments manage certain types of filings.

When you're building complex market research models, this MCP acts like a direct pipeline to official records. Because Vinkius hosts and manages this connection, you get immediate access across your preferred AI client, letting you spend time analyzing the data instead of figuring out where to find it.

Built · Hosted · Managed by Vinkius CVM Dados Abertos MCP - Brazilian Market Data

Server ID 019e3883-bbdc-7328-8291-e7724a419723

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

What Changes When You Connect

Instead of clicking through directories to find registration files, you can use search_datasets to pinpoint specific filings for investment funds instantly. This saves hours of manual searching.

You don't have to guess what data exists. Use list_datasets first; it gives you a full list of every available package on the CVM portal at a glance.

Need to know who published the data? Use list_organizations to map out which specific CVM departments are responsible for certain sets, helping with compliance verification.

When you find a dataset name using get_dataset, you can immediately follow up by calling get_resource to get direct links and metadata for the actual CSV or XML files ready for download.

This MCP helps Data Scientists automate discovery. You can list all relevant groups via list_groups before targeting the specific resources, building a reliable data pipeline.

See it in action

01 01

A compliance officer needs to audit regulatory filings.

They ask their agent to run list_organizations first, identifying which department published the necessary reports. Then they use that information with search_datasets to find all relevant documents for a specific company.

02 02

A financial analyst is researching fund performance.

Instead of downloading dozens of PDFs, they ask their agent to run get_dataset on 'Investment Funds' and then use the metadata to get direct resource links via get_resource, feeding structured data into a spreadsheet.

03 03

A data scientist needs to understand all available market types.

They start by using list_groups to categorize the whole market, then use that context to run search_datasets for 'Companhias Abertas' to ensure they haven't missed any major data sources.

04 04

A researcher needs a quick overview of all available data types.

They simply ask the agent to use list_datasets, immediately seeing packages like 'fi-cad' and 'infodiario,' giving them a map of every possible data source in one step.

The honest tradeoffs

Searching for everything at once

Anti-pattern

Asking the agent, 'Give me all the fund reports and company filings.' This is too vague; it lacks specific parameters.

The Fix

You need to narrow the scope. First, use list_groups to identify the correct category (like 'Fundos de Investimento'), then use that group name with search_datasets for a precise result.

Assuming resource links are available

Anti-pattern

Simply asking for 'the latest filing.' The system can't guess which file you need or what format it’s in.

The Fix

Always get the package details first. Use get_dataset to understand the structure, then use get_resource with the specific dataset ID to retrieve the actual download metadata.

Overlooking data ownership

Anti-pattern

Finding a report but having no idea if the CVM department is reliable or responsible for its updates.

The Fix

Before trusting the data, use list_organizations to check which group published it. This verifies the source and helps confirm data integrity.

When It Fits, When It Doesn't

Use this MCP if your goal is structured market research: finding official filings, comparing dataset metadata, or mapping out regulatory sources across Brazilian finance. It's ideal for compliance and analysis where you need to discover available information.

Don't use it if you need real-time trading data (like current stock prices) or transactional functions like 'send a message.' This MCP is read-only discovery. If your workflow requires complex, multi-step transformation between different external systems, consider an API gateway tool instead of relying on the structured query tools like list_datasets alone.

Questions you might have

How do I list all available data packages using `list_datasets`? +

You call list_datasets with no arguments. This command returns a full inventory, showing you every dataset package on the CVM portal that your agent can access.

Can I find filings for 'fundos' using `search_datasets`? +

Yes, use search_datasets and pass 'fundos' as the query term. The system will return specific dataset names like 'fi-cad,' which you can then investigate further.

What is the difference between `get_dataset` and `get_resource`? +

get_dataset gives you metadata about a whole collection (the container). get_resource gets details about one specific file, like its download link or format.

Do I need an API key for `list_organizations`? +

While the tool can run publicly, providing your CVM API Key is always recommended. It increases your usage limits and makes sure your agent doesn't hit a rate limit during large searches.

What should I do if `search_datasets` returns zero results for a specific topic? +

The tool indicates no direct match. Check your spelling, or try broadening the search terms. You might need to use list_groups first to find the correct thematic area before searching again.

How do I map a data set back to its originating department using `list_organizations`? +

The system lists all publishing bodies. To narrow it down, you should combine the results from list_datasets with specific organizational names you find here.

If I use `get_dataset`, how do I actually get the download link for a CSV file? +

You must run get_resource after getting the metadata. The dataset tells you what data exists, but the resource tool retrieves the direct links and specific file details.

What happens if I hit rate limits when using multiple tools like `list_datasets`? +

The MCP will return an explicit error code indicating your current limit. For high-volume work, you'll need to manage requests or consider the optional API key for higher usage tiers.

How can I find the most recent data for a specific investment fund? +

Use the search_datasets tool with keywords like 'fundos' or 'fi-cad'. Once you identify the dataset, use get_dataset to list all available resources, which typically include the most recent CSV files.

Can I get the direct download link for a data file? +

Yes! Use the get_resource tool with a specific Resource ID. The response will include the url field, which is the direct link to the raw data (e.g., a CSV file).

What are thematic groups in the CVM portal? +

Thematic groups categorize datasets by market segment. Use list_groups to see categories like 'Fundos de Investimento', 'Companhias', and 'Auditores Independentes' to better navigate the available data.

Connect to your AI in seconds.

List groups

List organizations

List datasets

CVM Dados Abertos: 6 Tools for Financial Research

Make your AI actually useful.

List Groups

List Organizations

List Datasets

Search Datasets

Get Dataset

Get Resource

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Navigating Brazilian financial data without a map is painful.

Getting Metadata with `get_dataset` provides immediate context.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

A compliance officer needs to audit regulatory filings.

A financial analyst is researching fund performance.

A data scientist needs to understand all available market types.

A researcher needs a quick overview of all available data types.

The honest tradeoffs

Searching for everything at once

Assuming resource links are available

Overlooking data ownership

When It Fits, When It Doesn't

Questions you might have