How to Use the CNJ (Datajud API Pública) MCP in Vercel AI SDK

Feed live Brazilian court data directly into your React components in real-time using Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CNJ (Datajud API Pública) MCP to Vercel AI SDK

Create your Vinkius account to connect CNJ (Datajud API Pública) to Vercel AI SDK 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 CNJ (Datajud API Pública) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct court record lookups with Vercel AI SDK

The `search_process_by_number` tool lets your agent fetch court records directly from TRF1 or TJSP without making users wait for heavy judicial queries to load. By hooking this MCP Server up to your edge functions, your agent can instantly call the tool and pipe the Brazilian lawsuit details straight into your UI. The raw JSON from the court API gets parsed instantly, letting your application render clean timelines of legal events. It bypasses the usual API middleware lag, giving your users immediate feedback on state and federal court filings.

Advanced Elasticsearch queries without backend boilerplate

Executing the `search_processes_advanced` tool allows your agent to run deep Elasticsearch queries directly against the Datajud API to pinpoint specific legal precedents. This lets your AI client build complex search filters based on your users' conversational requests. Your frontend handles the rest, rendering the returned judicial records as they arrive. This setup eliminates the need to maintain your own Elasticsearch wrapper or manage complex Brazilian court API keys in your client code.

Filter by class and organ on the fly

With the `search_processes_by_class_and_organ` tool, your agent can filter court cases by specific procedural classes and court organs instantly. Legal teams can narrow down the noise and pull exactly what matters without navigating complex government portals. Because this runs over a lightweight MCP connection, the response feeds right into your streaming state. You get a clean, reactive dashboard that updates as fast as the National Council of Justice processes the query.

Setup guide

Set up CNJ (Datajud API Pública) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all CNJ (Datajud API Pública) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent CNJ (Datajud API Pública) transactions",
});

console.log(text);
await mcpClient.close();

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 CNJ Datajud. 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 CNJ (Datajud API Pública) 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 CNJ (Datajud API Pública) MCP in Vercel AI SDK

Install the MCP client package, initialize it with the HTTP transport URL, and pass the tools to your text generation functions. Don't forget to close the client connection once the stream finishes.

Yes. The server returns structured JSON that your streaming UI components can parse on the fly, showing real-time court updates without blocking the thread.

Yes, the server is built to run in lightweight environments. You can trigger court searches from Vercel Edge Functions without hitting timeout limits or inflating your bundle size.

The server manages the connection pooling and authentication. Your SDK calls receive clean error payloads if the Brazilian court endpoints throttle, allowing you to handle UI retries gracefully.

All queried lawsuit records and court documents pass through a secure, ephemeral V8 isolate. Vinkius never caches your legal search queries or stores the retrieved court documents on its servers.

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