How to Use the Docket Alarm MCP in OpenAI Agents SDK

Q: How do I connect the Docket Alarm MCP Server to my OpenAI Agents SDK pipeline?

You install the SDK, then initialize the server using the MCPServerStreamableHttp class with your Vinkius endpoint. Pass this server object into your Agent constructor's mcpservers list. The agent automatically discovers all thirteen tools at startup without extra configuration.

Q: Can my OpenAI Agents SDK setup automate alerts for new filings using Docket Alarm?

Yes, your agent can run the trackcase tool to register any active docket for automatic monitoring. This sets up background alerts so you get notified the moment a new document is filed in that specific court.

Q: What is the best way to run natural language searches across court records?

Use smartsearch to convert plain English instructions into complex, precise search queries. This tool formats the query syntax automatically so your agent finds relevant filings without failing on complex search operators.

Run autonomous litigation tracking agents using OpenAI Agents SDK to connect to this MCP Server and monitor 732 million court records.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Docket Alarm MCP to OpenAI Agents SDK

Create your Vinkius account to connect Docket Alarm 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 Docket Alarm with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Court Tracking via OpenAI Agents SDK

The `get_docket` tool fetches live court dockets directly from state and federal databases, bypassing cached data when you need absolute accuracy. You configure your agent to monitor active cases and immediately trigger downstream actions when new filings land. This prevents missed deadlines and keeps your legal team ahead of sudden court updates. To keep tabs on ongoing litigation, feed the output of your live searches into `track_case` to set up automatic alerts. When your OpenAI agent runs this MCP Server tool, it registers your target case for continuous monitoring. You don't have to write custom polling loops or maintain fragile web scrapers to keep your case files current.

Automated Complaint Analysis

The `get_complaint_summary` tool is an MCP capability that extracts targeted summaries from lengthy, complex legal filings without requiring manual reading. Your agent can ingest raw complaint text and isolate the core allegations in seconds. This allows your intake pipeline to flag high-risk lawsuits before they get assigned to an attorney. You can chain this with `get_cause_of_action` to identify the specific statutes and legal grounds cited in the complaint. The agent parses the structural layout of the filing to map out exactly what laws the plaintiff claims were broken. This speeds up the initial case assessment from hours to a few minutes.

Judgment Extraction and Case Matching

The `extract_judgment` tool pulls final outcomes, damages, and rulings directly from messy court orders. Instead of having junior associates read hundreds of pages of PDFs, your agent isolates the exact legal resolution. This feeds clean, structured outcome data directly into your firm's internal database. When you only have partial case names or numbers, use `match_case` to find the exact legal record. This MCP tool resolves noisy or incomplete data inputs using specialized matching algorithms. This keeps your records accurate even when client intake forms contain typos or missing information.

Setup guide

Set up Docket Alarm 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 Docket Alarm tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Docket Alarm 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="Docket Alarm Agent",
            instructions="You have access to Docket Alarm 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 Docket Alarm. 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 Docket Alarm 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 Docket Alarm MCP in OpenAI Agents SDK

You install the SDK, then initialize the server using the `MCPServerStreamableHttp` class with your Vinkius endpoint. Pass this server object into your Agent constructor's `mcp_servers` list. The agent automatically discovers all thirteen tools at startup without extra configuration.

Yes, PACER charges a fee of ten cents per page of results when using `search_pacer` unless you set the test parameter to true. Your agent should use this flag during development to avoid unexpected charges. For state courts, you can use `search_direct` to query local jurisdictions without PACER fees.

Yes, your agent can run the `track_case` tool to register any active docket for automatic monitoring. This sets up background alerts so you get notified the moment a new document is filed in that specific court.

Use `smart_search` to convert plain English instructions into complex, precise search queries. This tool formats the query syntax automatically so your agent finds relevant filings without failing on complex search operators.

All queries, PACER credentials, and fetched court records transit through a zero-trust, ephemeral V8 isolate sandbox. Your search history and raw docket data are never stored or used to train public models. Connection tokens are managed securely on Vinkius, ensuring your firm's search patterns remain completely confidential.

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