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

Enforce strict schema validation on Brazilian judicial data with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect CNJ (Datajud API Pública) to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe process searches in Pydantic AI

The `search_process_by_number` tool returns data that your agent validates against Pydantic models. You get clean, typed objects instead of raw dictionaries. If the Datajud API returns a malformed response, the agent stops before processing bad data. This keeps your pipeline predictable.

Elasticsearch queries for Pydantic AI agents

Use `search_processes_advanced` to run complex searches while relying on Pydantic AI to enforce the result structure. It ensures your agent only handles data that matches your expected schema. You define the model, and the tool fills it. It removes the risk of silent failures when the underlying API changes.

Categorized search for Pydantic AI

The `search_processes_by_class_and_organ` tool allows you to pull structured lists of cases. Pydantic AI validates each record against your defined court classes. This makes it easy to handle multiple results without writing custom parsing logic. Your agent stays focused on the legal analysis.

Setup guide

Set up CNJ (Datajud API Pública) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "cnj-datajud-api-publica-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to CNJ (Datajud API Pública) tools.",
)

result = await agent.run("List recent CNJ (Datajud API Pública) transactions")
print(result.output)

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 Pydantic AI

Define a Pydantic model for the expected response. When the tool returns data, the framework automatically checks it against your model before the agent proceeds.

The agent will raise a validation error immediately. This prevents corrupted data from entering your processing logic.

Yes. The MCP implementation is model-agnostic. You can switch between OpenAI, Anthropic, or local models without changing your tool definitions.

The server runs externally, and the library supports both Streamable HTTP and SSE. Just point the MCPToolset to your Vinkius endpoint.

The server operates in a zero-trust environment. It only processes public procedural records, and your Pydantic schemas ensure no unauthorized fields are ever ingested.

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