How to Use the CourtListener MCP in OpenAI Agents SDK

Q: How do I handle rate limits when using CourtListener with the OpenAI Agents SDK?

Set cacheToolsList=True in your HTTP server parameters to avoid redundant schema lookups. The SDK caches the tool definitions for searchopinions and listcourts locally, saving your API quota for actual legal queries.

Q: How does the OpenAI Agents SDK validate inputs for CourtListener tools?

The SDK inspects the JSON schema for tools like getopinion before sending the request. If the model generates a malformed opinion ID, the SDK rejects the call before it hits the live API.

Run production OpenAI agents that pull real-time court dockets and judge records with built-in execution guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect CourtListener to OpenAI Agents 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 CourtListener with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarded Docket Searches in OpenAI Agents

Your OpenAI agent uses `search_dockets` to pull live case files from the CourtListener MCP Server. Because you are running in production, the SDK intercepts the tool call, validating the query parameters before your agent executes the search against the PACER-backed database. If an agent tries to hallucinate a docket number, the validation layer stops it cold. You get clean, verified docket histories streamed directly into your agent's context window without risking bad API requests.

Multi-Agent Judge Profiling

Specialized agents hand off tasks to compile deep judicial backgrounds using the CourtListener MCP tools. One agent pulls the judge's bio using `get_judge`, while a financial auditor agent analyzes their disclosures with `list_financial_disclosures` to find potential conflicts. The OpenAI dashboard tracks this multi-agent chain of thought. You see exactly when the handoff occurs and how the financial data flows between your specialized nodes.

Citations Mapping with Traced Execution

Your autonomous agent maps precedent by triggering `list_citations` and `get_opinion` in a recursive loop through the MCP interface. The OpenAI Agents SDK manages these tool calls safely, preventing run-away execution loops that drain your API credits. Every single opinion retrieved is logged in your tracing dashboard. You can audit the legal reasoning step-by-step to see exactly which citation triggered the agent's final legal conclusion.

Setup guide

Set up CourtListener MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CourtListener tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CourtListener tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CourtListener tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CourtListener Agent",
            instructions="You have access to CourtListener tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Set `cacheToolsList=True` in your HTTP server parameters to avoid redundant schema lookups. The SDK caches the tool definitions for `search_opinions` and `list_courts` locally, saving your API quota for actual legal queries.

You build specialized agents that pass control back and forth. For instance, a research agent uses `search_opinions` to find cases, then hands the results to a writing agent that drafts the brief.

The SDK inspects the JSON schema for tools like `get_opinion` before sending the request. If the model generates a malformed opinion ID, the SDK rejects the call before it hits the live API.

No. The SDK auto-discovers all ten legal research tools from the MCP Server when you pass the Vinkius HTTP endpoint to the agent constructor.

Your search queries and retrieved judge financial disclosures process inside an isolated V8 sandbox. Vinkius uses ephemeral execution, meaning the server forgets your API tokens and legal data the millisecond the request completes.

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