How to Use the CVM Dados Abertos MCP in Pydantic AI

Q: How do I configure CVM Dados Abertos with Pydantic AI?

You initialize MCPToolset with your Vinkius server URL and pass it to the toolsets parameter of your Agent. The agent automatically discovers MCP tools like searchdatasets and enforces runtime type checks on their outputs.

Q: Does Pydantic AI validate the output of CVM Dados Abertos tools?

Yes, the framework validates all data returned by getdataset against strict internal schemas. If the CVM portal changes its metadata format, Pydantic AI raises a validation error.

Q: Can I use CVM Dados Abertos with local models in Pydantic AI?

Yes, Pydantic AI is model-agnostic. You can pair the listgroups tool with local models or commercial APIs depending on your cost and privacy requirements.

Q: How do I migrate from old MCP implementations to CVM Dados Abertos in Pydantic AI?

Use the unified MCPToolset class rather than the deprecated MCPServerHTTP client. This manages the connection to your Vinkius endpoint and registers the CVM tools in one step.

Run type-safe queries against Brazilian capital markets using CVM Dados Abertos and Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect CVM Dados Abertos to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe CVM Schema Discovery via Pydantic AI

This MCP Server validates Brazilian financial metadata at the runtime boundary using `list_datasets` and `search_datasets` within your Pydantic AI agent. If the CVM portal returns an unexpected response format, the framework raises a validation error immediately rather than letting bad data corrupt your database. You register the MCP server using the `MCPToolset` class, which handles the underlying HTTP communication. Your agent can safely inspect investment fund registries, knowing every field matches your strict Python type hints.

Validate Brazilian Market Resources

The server fetches structural metadata for specific financial assets through `get_resource` and `get_dataset` to ensure data integrity. Pydantic AI enforces type safety on these payloads, preventing your agent from hallucinating fields or processing malformed resource links. This strict runtime validation is critical when building automated compliance pipelines. If a dataset's structure changes on the CVM portal, your application fails loudly and safely before any bad data enters your production systems.

Categorize Financial Entities Safely

This toolset retrieves thematic groups and publishing bodies via `list_groups` and `list_organizations` to classify Brazilian market participants. Pydantic AI parses these lists into strongly-typed models, making it easy to filter corporate filers and fund managers. You use these typed outputs to route data pipelines to the correct processing service. Because the structures are validated at the boundary, you write clean, warning-free Python code without defensive try-except blocks.

Setup guide

Set up CVM Dados Abertos MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "cvm-dados-abertos-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to CVM Dados Abertos tools.",
)

result = await agent.run("List recent CVM Dados Abertos transactions")
print(result.output)

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 Pydantic AI

You initialize `MCPToolset` with your Vinkius server URL and pass it to the `toolsets` parameter of your `Agent`. The agent automatically discovers MCP tools like `search_datasets` and enforces runtime type checks on their outputs.

Yes, the framework validates all data returned by `get_dataset` against strict internal schemas. If the CVM portal changes its metadata format, Pydantic AI raises a validation error.

Yes, Pydantic AI is model-agnostic. You can pair the `list_groups` tool with local models or commercial APIs depending on your cost and privacy requirements.

Use the unified `MCPToolset` class rather than the deprecated `MCPServerHTTP` client. This manages the connection to your Vinkius endpoint and registers the CVM tools in one step.

The integration processes only public Brazilian capital market datasets and group metadata. All transit is encrypted via HTTPS, and Vinkius runs the server in an ephemeral sandbox to guarantee no persistent logs of your financial queries are kept.

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