Compatible with every major AI agent and IDE
What is the CNJ (Datajud API Pública) MCP Server?
Connect to the CNJ Datajud Public API to perform deep searches across the Brazilian judicial system. This server allows AI agents to retrieve detailed metadata about lawsuits, court movements, and procedural history directly from the official national database.
What you can do
- Search by CNJ Number — Retrieve full details of a specific lawsuit using its unique unformatted numbering and the target court alias.
- Class & Organ Filtering — Find processes categorized by their Procedural Class (TPU) and specific Court Organ codes.
- Advanced Elasticsearch Queries — Execute complex searches using the full power of Elasticsearch Query DSL to filter by dates, parties, or specific metadata fields.
- Court Coverage — Access data from various courts including TRFs, TJs, TST, and more via their respective API aliases.
How it works
- Subscribe to this server
- Enter your CNJ Datajud API Key
- Start querying the Brazilian judicial database from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Legal Professionals — Quickly check the status and history of lawsuits without manual portal navigation.
- Compliance Teams — Automate background checks and legal risk assessments using official government data.
- Researchers & Analysts — Perform bulk queries and advanced data extraction for legal statistics and trends.
Built-in capabilities (3)
g., api_publica_trf1, api_publica_tjsp). Search for a specific judicial process by its CNJ number
Execute an advanced Elasticsearch query against the Datajud API
Search processes by Procedural Class and Court Organ
Why Mastra AI?
Mastra's agent abstraction provides a clean separation between LLM logic and CNJ (Datajud API Pública) tool infrastructure. Connect 3 tools through Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution. deployable to any Node.js host in one command.
- —
Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure. add CNJ (Datajud API Pública) without touching business code
- —
Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation
- —
TypeScript-native: full type inference for every CNJ (Datajud API Pública) tool response with IDE autocomplete and compile-time checks
- —
One-command deployment to any Node.js host. Vercel, Railway, Fly.io, or your own infrastructure
CNJ (Datajud API Pública) in Mastra AI
CNJ (Datajud API Pública) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect CNJ (Datajud API Pública) to Mastra AI 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 CNJ (Datajud API Pública) in Mastra AI
The CNJ (Datajud API Pública) 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 3 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Mastra AI 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
CNJ (Datajud API Pública) for Mastra AI
Every tool call from Mastra AI to the CNJ (Datajud API Pública) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I find a process if I only have the CNJ number?
Use the search_process_by_number tool. You will need the unformatted digits of the process and the specific court alias (e.g., api_publica_tjsp for São Paulo State Court).
Can I list multiple processes from a specific court organ?
Yes, use search_processes_by_class_and_organ. Provide the court alias, the procedural class code, and the organ code. You can also control the result size and use pagination.
What is the 'Advanced Search' tool for?
The search_processes_advanced tool allows you to send a raw Elasticsearch query body. This is useful for complex filtering that isn't covered by standard search tools, such as filtering by specific dates or nested metadata.
How does Mastra AI connect to MCP servers?
Create an MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.
Can Mastra agents use tools from multiple servers?
Yes. Pass multiple MCP clients to the agent constructor. Mastra merges all tool schemas and the agent can call any tool from any server.
Does Mastra support workflow orchestration?
Yes. Mastra has a built-in workflow engine that lets you chain MCP tool calls with branching logic, error handling, and parallel execution.
createMCPClient not exported
Install: npm install @mastra/mcp
Explore More MCP Servers
View all →
ScrapingBee
10 toolsScrape websites without getting blocked using headless browsers, proxy rotation, and JavaScript rendering handled for you.

Cohere (Embed & Rerank)
6 toolsEmpower RAG via Cohere — generate high-quality text embeddings, rerank documents for better accuracy, and perform AI classification directly from any AI agent.

ZeroTier
13 toolsManage ZeroTier virtual networks, authorize members, and monitor local node status directly from your AI agent.

HeyGen
11 toolsAutomate AI video generation via HeyGen — manage avatars, videos, and templates directly from any AI agent.
