Compatible with every major AI agent and IDE
What is the Minas Gerais (Estado) MCP Server?
Connect to the Minas Gerais State Open Data Portal to explore a vast repository of public information. This server allows AI agents to programmatically browse, search, and retrieve metadata from one of Brazil's most comprehensive transparency portals.
What you can do
- Dataset Discovery — List all available packages or search for specific datasets related to health, education, or finance using
list_packagesandsearch_packages. - Organizational Insights — Explore the structure of the state government by listing departments and viewing their specific datasets via
list_organizationsandget_organization. - Resource Access — Identify specific files (CSV, PDF, XLS) within datasets and retrieve their metadata using
get_resourceandsearch_resources. - Categorized Browsing — Navigate data through thematic groups (categories) or tags to find exactly what you need with
list_groupsandlist_tags.
How it works
- Subscribe to this server
- (Optional) Enter your Minas Gerais Portal API Key for higher rate limits
- Start querying public data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Data Analysts — quickly find and inspect public datasets for research and reporting
- Journalists — automate the discovery of government transparency data and organizational structures
- Developers — integrate official state data into applications without manual portal navigation
Built-in capabilities (10)
Get details and datasets of a group
Get details and datasets of an organization
Get full metadata of a specific dataset
Get metadata of a specific resource (file)
List all groups (categories)
List all organizations
List all dataset names in the portal
List all tags used in the portal
Search for datasets matching specific criteria
Search for resources matching a query
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 10 tools from Minas Gerais (Estado) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Minas Gerais (Estado), another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Minas Gerais (Estado) in OpenAI Agents SDK
Minas Gerais (Estado) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Minas Gerais (Estado) to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Minas Gerais (Estado) in OpenAI Agents SDK
The Minas Gerais (Estado) 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. All 10 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* 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
How Vinkius secures
Minas Gerais (Estado) for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Minas Gerais (Estado) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I find datasets related to a specific topic like 'health'?
You can use the search_packages tool with the query 'saude' or use get_group with the ID 'saude' to list all datasets categorized under that theme.
Can I see the actual download links for the data files?
Yes. By using get_package with a dataset ID, the AI will retrieve the metadata for all associated resources, which typically includes the URL, format (CSV, PDF), and description of each file.
How do I list all government agencies that publish data on the portal?
Use the list_organizations tool. It will return a list of all government bodies (like CGE, SEF, etc.) that have active datasets in the Minas Gerais portal.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Richards CRM
11 toolsAutomate project management via Richards CRM — manage leads, estimates, and material orders with AI.

Moneybird
12 toolsHandle Dutch and European accounting with automated invoicing, bank reconciliation, and tax-ready financial reports.

Kissflow
9 toolsBuild low-code workflows, process apps, and case management solutions that digitize operations without heavy IT involvement.

Blockdaemon (Blockchain Infrastructure)
4 toolsAccess institutional-grade blockchain data across multiple protocols — list blocks, track transactions, and retrieve financial reports via Blockdaemon Ubiquity.
