STF Dados Abertos MCP for AI. Analyze Brazilian judicial records with AI.
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
STF Dados Abertos connects your AI client directly to the Brazilian Supreme Federal Court's open data portal. You can list all available datasets, search for specific legal topics, and run structured queries against massive judicial records without downloading files.
It gives you immediate access to metadata, organizational structures, and query results from Brazil’s largest public legal repository.
What your AI can do
Get group
Retrieves the detailed metadata and information for a specified organizational group within STF Dados Abertos.
Get organization
Fetches comprehensive details about a specific institutional organization that contributes data to the portal.
Get package
Gets all available metadata and resource links for an entire dataset (package).
List all available datasets or search the catalog using keywords to pinpoint relevant legal packages.
Perform targeted, SQL-like queries directly on data resources without downloading entire files.
Retrieve deep metadata for specific datasets (packages) or individual files (resources), revealing their structure and update history.
List and inspect the organizational groups and institutions responsible for maintaining the open data, showing its source.
Filter the entire catalog of available datasets by specific keywords or criteria.
Ask an AI about this
Waiting for input…
STF Dados Abertos MCP Server: 9 Tools for Legal Data Access
These nine tools let your AI client interact with the entire STF open data API, allowing you to find, inspect, and query legal records programmatically.
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 STF Dados Abertos on VinkiusGet Group
Retrieves the detailed metadata and information for a specified organizational group within STF Dados Abertos.
Get Organization
Fetches comprehensive details about a specific institutional organization that...
Get Package
Gets all available metadata and resource links for an entire dataset (package).
Get Resource
Retrieves detailed information, including formats and size, for a specific data file...
List Groups
Lists all available organizational groups that categorize the open data sets.
List Organizations
Provides a list of all institutional organizations contributing to STF Dados Abertos.
List Packages
Lists every available dataset package hosted on the STF open data portal.
Search Datastore
Runs structured, SQL-like queries against a specific resource's live data store to...
Search Packages
Searches the entire catalog of datasets using keywords and filters to find relevant...
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.
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
Make Your AI Do More
Start with STF 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 STF 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
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 9 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Finding judicial records shouldn't require clicking through five different government tabs.
Today, accessing official transparency data means opening dozens of departmental portals. You click into a 'Datasets' tab, then select the right package, and finally filter by year or department. If you miss one step or forget to download a massive zip file, your analysis breaks.
With this server, you just tell your agent what you need—like, 'Show me all labor law spending from 2021.' Your AI client executes `search_packages` and then runs the targeted query using `search_datastore`. You get a clean table of results instantly.
STF Dados Abertos MCP Server: Get metadata, not just data.
The painful manual steps are the cross-referencing. You find Dataset A and need to know its update frequency; you open a new tab to check the 'metadata' section. Then you switch to Dataset B and repeat the process for its resource details.
Now, running `get_package` or `get_resource` gives you all that data—provenance, structure, update cycle—in one structured output. You know exactly what you’re dealing with before your agent pulls a single value.
What your AI can actually do with this
Yo, listen up. This server hooks your AI agent straight into the Brazilian Supreme Federal Court's open data portal—STF Dados Abertos. Forget downloading massive files just to find one piece of info; this lets you run structured queries and analyze judicial records using natural language prompts. It gives you immediate access to deep metadata, organizational structure, and query results from Brazil’s biggest public legal repository without the headache.
When you're scoping out what data's available, you start by listing everything. You can use list_packages or search_packages to see every dataset package hosted on the portal, or you can narrow it down fast by running a keyword search across the whole catalog. Need something specific? Running a targeted search with search_packages lets you pinpoint relevant legal packages immediately.
Once you've found a potential dataset, you need to know what you're dealing with. You can use get_package to get all the metadata and resource links for an entire package. If you want details on just one file within that set—the format, size, or specific record info—you run get_resource. For a deeper dive into a dataset’s structure, get_metadata pulls comprehensive information about what's inside.
This whole process lets you map out the data's exact shape before running any queries.
If you know roughly where your data lives, you can find it by listing all available organizational groups using list_groups. From there, you can drill down to get detailed metadata and information for a specific group using get_group, or you can learn about the source itself with list_organizations which gives you a list of every institution contributing data.
To see who's behind the curtain, run get_organization to fetch comprehensive details on any single institutional organization.
Now comes the good part: querying the live stuff. You don’t wanna download gigabytes just to check three rows, right? That's where search_datastore shines. It lets you perform structured, SQL-like queries directly against a resource's live data store, pulling out exactly the targeted information you need instantly.
This setup gives your AI client granular control over judicial and institutional data. You can first list all available organizational groups with list_groups, then check which institutions are feeding that data using list_organizations. By pairing those calls with get_organization or get_group, you trace the entire data provenance—you know exactly who's responsible for maintaining the open data sets.
If you suspect a certain dataset is key, run get_package to inspect its metadata and resource links. To find that package in the first place, use search_packages with your keywords. Once selected, if you want deep structural details on any file, check it with get_resource. Remember, running search_datastore is your main tool for getting answers without downloading a single mega-file.
019e38f4-0d1b-70c9-b33b-9f3302674d92 Here's how it actually works
The bottom line is: Your AI client talks to STF, and you get the answer without ever visiting a browser page.
Subscribe to this server and provide your API key, if required.
Send a natural language query (e.g., 'List all packages related to labor law').
The agent uses the appropriate tool (list_packages, search_packages, etc.) and returns structured metadata or data results directly in your chat.
Who is this actually for?
Anyone dealing with large volumes of public-facing government or legal data needs this. It's for the researcher who can't spend hours clicking through complex portals, and the analyst who needs verifiable, structured data points fast.
Uses search_packages to narrow down datasets by legal topic, then uses get_resource to verify the structure of specific judicial records.
Runs automated checks using list_groups and search_datastore to track changes in public spending or institutional reporting over time.
Uses the tools to map out which departments (via get_organization) are responsible for specific types of publicly available data, helping with compliance audits.
What Changes When You Connect
Skip manual browsing. Instead of clicking through menus to find a dataset, simply use search_packages and tell your agent what you need by topic or keyword.
Stop downloading huge ZIP files just to check one column. Use search_datastore to run precise queries on live data resources directly in the chat output.
Know where your data comes from. By calling get_organization, you immediately map which department maintained a dataset, giving instant provenance context.
Get the full picture of a data set's structure using get_package. This gives you all resource details and metadata upfront—no guessing what files are available.
Build your knowledge graph. Use list_groups and list_organizations to systematically map out the entire institutional network contributing to STF’s open data.
See it in action
Tracking changes in public spending
A journalist needs to compare budget allocations across three different years. Instead of opening three separate datasets and cross-referencing dates, they ask their agent to use list_packages to find the correct financial records, then run targeted queries with search_datastore to pull comparative figures into one output.
Investigating a legal precedent
A law student needs facts from an obscure case file. They use search_packages for 'precedent' and then, when they find the correct package, they run get_resource to inspect the available files before asking the agent to retrieve specific data points using get_package details.
Mapping institutional responsibility
A corporate compliance analyst needs to know who owns a particular type of public record. They use list_organizations and then drill down with get_organization until they identify the exact responsible department, documenting the data source's ownership.
Validating dataset scope
A developer integrating STF data needs to know if a resource contains salary information. They first use search_packages to find the payroll package, then they call get_resource and inspect the metadata fields before writing any integration code.
The honest tradeoffs
Treating it like a simple search engine
Prompting: 'Tell me about labor law data.' This gets you links, but no actual structured information or resource details.
Use search_packages first to confirm the correct dataset name. Then, use that package name with get_package to see which specific resources are available before asking for data extraction.
Downloading everything
Manually navigating to a large resource and downloading dozens of MBs of CSV/JSON just to check 10 rows.
Don't download. Use search_datastore directly on the specific resource ID. This allows your agent to pull only the 10 required rows based on criteria you define.
Ignoring data source context
Assuming all legal data is in one place without checking who owns it.
Always check the lineage. Run list_groups and then use get_group to understand which organizational unit manages the dataset, ensuring your findings are accurate.
When It Fits, When It Doesn't
Use this server if you need verifiable, structured data from Brazilian government or judicial sources (STF). You should run it when your goal is to query metadata—who owns it (get_organization), what files exist (list_packages), or what the values are (search_datastore).
Don't use this if you need general web scraping, unstructured text analysis from arbitrary websites, or data from non-Brazilian sources. For those tasks, you’ll need a different type of tool that specializes in document processing or general web crawling. If your goal is simply to browse the site like a human, manually navigating the portal may still be faster than prompt engineering.
Questions you might have
How do I find all available dataset packages using list_packages? +
Run the list_packages tool directly. This provides an immediate catalog of every major dataset category published by STF, giving you a starting point for your research.
Can I run SQL queries on the data in STF Dados Abertos using search_datastore? +
Yes. search_datastore allows you to write structured queries against specific resources. This lets you filter and extract exact information without having to download large, raw files.
How do I check the metadata for a whole dataset using get_package? +
Pass the package ID to get_package. This tool fetches comprehensive details, showing you all related resources and the overall structure of the data before you start querying.
What is the difference between list_groups and list_organizations? +
Use list_groups to see how the open data is categorized (the thematic groups). Use list_organizations to see which specific institutional bodies are responsible for creating or maintaining that data.
What specific details about an individual data file does the `get_resource` tool provide? +
It gives deep metadata for a single resource ID. You retrieve details like the file format (CSV, JSON), exact size in bytes, and the precise timestamp of when it was last updated.
How do I refine my search to narrow down available datasets using `search_packages`? +
The tool filters the entire dataset catalog based on keywords you provide. You pass a topic or phrase, and it returns a list of matching package IDs, so you don't have to sift through irrelevant results.
If my data queries hit the default rate limit, how do I increase my access capacity? +
You must provide your STF API Key in the server settings. Using this key bypasses standard usage limits and grants you higher request quotas for repeated or large-scale querying.
Using `get_organization`, how do I determine who is responsible for a specific data package? +
You use the tool with the relevant organizational ID. This pulls details about the maintainer group, showing their official scope and purpose within the court's structure.
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.
We've already built the connector for STF Dados Abertos. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 9 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.