How to Use the UniCourt MCP in Pydantic AI

Q: How does UniCourt help me search for cases with Pydantic AI?

You use the searchcases tool. The results are type-checked against a schema, so your agent only receives predictable data fields.

Q: Can I track updates on UniCourt records using Pydantic AI?

Yes. Use trackcase. When the status changes, the returned object is validated against the defined model, preventing runtime errors in your code.

Q: What tools are available for importing cases with UniCourt using Pydantic AI?

You can either run importcase for high-priority imports or use importpacercase to bring in records not yet part of the UniCourt database.

Ensure perfect legal data structure validation with your AI client.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UniCourt MCP to Pydantic AI

Create your Vinkius account to connect UniCourt 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 UniCourt with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Structured Data Retrieval for Pydantic AI

When you call `get_case`, the agent returns case details validated against a Pydantic model. You never get unexpected data; if UniCourt sends garbage, your agent fails loudly. It's the same process when checking status with `get_case_update_status`. The output is always predictable, keeping your pipelines running cleanly.

Searching and Tracking Data via MCP Server

Need to search cases? Call `search_cases` and the results are immediately validated. This guarantees that any case name or ID you work with is correctly formatted. For continuous monitoring, use `track_case`. The scheduled updates always pass validation checks before your agent uses them.

Credential Management for Pydantic AI

Managing credentials doesn't have to be a risk. Use the `update_pacer_credential` tool to handle PACER access. The output is structured and typed, so you know exactly what you got back. If you need initial data, running `get_norm_attorney` gives you normalized attorney details that fit perfectly into your established Python models.

Setup guide

Set up UniCourt 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": {
        "unicourt-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent UniCourt 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 UniCourt. 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 UniCourt 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 UniCourt MCP in Pydantic AI

You use the `search_cases` tool. The results are type-checked against a schema, so your agent only receives predictable data fields.

Yes. Use `track_case`. When the status changes, the returned object is validated against the defined model, preventing runtime errors in your code.

This server touches case records and document orders. The use of Pydantic ensures that even if the underlying API data is complex, what reaches your application is strictly typed and validated.

You can either run `import_case` for high-priority imports or use `import_pacer_case` to bring in records not yet part of the UniCourt database.

Yep. You can search and get details on parties, judges, or law firms using tools like `search_norm_party`. The output data always conforms to your expected types.

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