How to Use the CourtListener MCP in Pydantic AI

Q: How do I configure the CourtListener toolset in Pydantic AI?

Initialize MCPToolset with your Vinkius HTTP endpoint and pass it directly to the Agent constructor. The older MCPServerHTTP class is deprecated, so stick to the unified toolset approach.

Q: Does this setup support live docket searches?

Yes, your agent calls searchdockets using the MCP tools to retrieve real-time case filings. The results are parsed and validated against your custom Pydantic models.

Build type-safe legal agents using Pydantic AI to validate CourtListener opinions and docket data at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CourtListener MCP to Pydantic AI

Create your Vinkius account to connect CourtListener 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 CourtListener with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Runtime Validation of MCP Server Legal Data

Your agent validates every court opinion fetched via the CourtListener MCP Server against strict Python types. Pydantic AI ensures that fields like publication date, author, and citation lists from `get_opinion` conform to your models before your application processes them. If the CourtListener API returns unexpected null values or modified data structures, the framework throws a validation error immediately. You catch API drifts in development instead of debugging corrupted data in production.

Type-Safe Docket Searches

Run structured legal queries using `search_dockets` without risking malformed payload errors. The model-agnostic agent maps the user's natural language request to your Pydantic schemas before executing the tool. This strict typing prevents LLMs from hallucinating invalid docket numbers or court IDs. You get clean, predictable dictionary structures back from every single search.

Structured Citation Extraction

Pydantic AI parses complex citation networks returned by `list_citations` into clean Python objects. Your agent can recursively trace legal precedent, knowing that each step of the journey is backed by runtime type guarantees. This setup works across OpenAI, Anthropic, or local models. You swap the underlying LLM without rewriting your legal data validation schemas.

Setup guide

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

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

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

The framework fails loudly and immediately if the data returned by `get_opinion` violates your schema. This prevents your legal agent from operating on malformed or hallucinated court records.

Yes, Pydantic AI is model-agnostic. You can connect your local Ollama instance to the CourtListener tools and still benefit from runtime type validation.

Initialize `MCPToolset` with your Vinkius HTTP endpoint and pass it directly to the `Agent` constructor. The older `MCPServerHTTP` class is deprecated, so stick to the unified toolset approach.

Yes, your agent calls `search_dockets` using the MCP tools to retrieve real-time case filings. The results are parsed and validated against your custom Pydantic models.

Your citation lists and raw court opinions are processed in memory within an isolated V8 sandbox. Vinkius handles the authentication token securely and never writes your legal search payloads to disk.

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