Bring Brazil Law
to OpenAI Agents SDK
Learn how to connect STF Dados Abertos to OpenAI Agents SDK and start using 9 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the STF Dados Abertos MCP Server?
Connect your AI agent to the STF Dados Abertos portal and explore the transparency data of the Brazilian Supreme Federal Court through natural language.
What you can do
- Dataset Discovery — List all available datasets (packages) and search for specific legal or administrative topics using keywords.
- Resource Inspection — Fetch detailed metadata for specific files, data links, and resources within a dataset to understand their structure.
- DataStore Querying — Perform SQL-like queries directly on DataStore-enabled resources to extract specific information without downloading large files.
- Institutional Browsing — Explore the organizations and groups that categorize and maintain the court's open data.
- Metadata Analysis — Access comprehensive metadata for packages, organizations, and groups to understand data provenance and update frequency.
How it works
- Subscribe to this server
- (Optional) Enter your STF API Key for higher access limits
- Start querying Brazilian judicial data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Legal Researchers — quickly find and analyze court datasets without manual portal navigation
- Data Journalists — automate the discovery of transparency data and resource updates for reporting
- Developers & Analysts — integrate official STF data into applications using structured metadata and DataStore queries
Built-in capabilities (9)
Get group details
Get organization details
Get dataset details
Get resource details
List groups
List organizations
List all datasets (packages) in STF Dados Abertos
Query DataStore
Search datasets
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 9 tools from STF Dados Abertos through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries STF Dados Abertos, 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
STF Dados Abertos in OpenAI Agents SDK
STF Dados Abertos and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect STF Dados Abertos 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 STF Dados Abertos in OpenAI Agents SDK
The STF Dados Abertos 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 9 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
STF Dados Abertos for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the STF Dados Abertos MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I perform SQL-like queries on the court's data files?
Yes! If a resource is integrated into the DataStore, you can use the search_datastore tool with the Resource ID to query the data within the file directly.
How do I find datasets related to a specific legal topic?
Use the search_packages tool. Simply provide a search term (e.g., 'processos' or 'votação') and the agent will return all matching datasets from the portal.
Is it possible to list all organizations that publish data on the STF portal?
Absolutely. Use the list_organizations tool to see all departments and entities, or get_organization to see details and datasets owned by a specific one.
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 →
Datadog
11 toolsMonitor applications via Datadog — query performance metrics, search logs, and list active monitors directly from any AI agent.
Digify
12 toolsShare documents securely with dynamic watermarks, access controls, and analytics that show exactly who viewed each page.
Egnyte
12 toolsStore and govern enterprise content with intelligent file management, access controls, and compliance monitoring across teams.
Dagster
6 toolsOrchestrate data pipelines via Dagster — monitor jobs, track runs, manage software-defined assets, and audit schedules directly from any AI agent.