How to Use the Docket Alarm MCP in Google ADK

Q: How do I configure the Docket Alarm MCP Server within my Google ADK agent?

You initialize the McpToolset class with your Vinkius HTTP URL and pass it to your LlmAgent constructor. The Gemini model auto-discovers the thirteen available tools, allowing it to query court records on demand.

Q: Can my Google ADK agent search federal records using Docket Alarm without incurring high fees?

Yes, but you must manage your queries carefully. The searchpacer tool charges ten cents per page of results, so you should use the test parameter during development. For broader, non-federal searches, run search against the cached database to minimize transactional costs.

Q: How does Docket Alarm handle queries for courts that require specific arguments in Google ADK?

Your agent should call getsearchdirectargs to discover the exact parameters required by a specific state or agency court. This prevents API errors by ensuring your Google ADK pipeline sends the correct fields before executing a live search.

Q: Can I use this setup to summarize long legal complaints?

Yes. Your agent can use getcomplaintsummary to extract concise bullet points or detailed overviews of newly filed lawsuits. This is ideal for feeding clean, structured case summaries directly into BigQuery or Vertex AI pipelines.

Feed live court records and docket updates directly into your Gemini enterprise agents with the Google ADK.

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 Google ADK

Create your Vinkius account to connect Docket Alarm to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Courts Directly via Google ADK

The `search_direct` tool queries state and agency courts directly to pull live filings into your Gemini agent's context window. This bypasses typical indexing delays, giving your team real-time access to local court dockets. Since Gemini handles massive token limits, you can feed entire dockets directly into your analytical models. To find out which jurisdictions you can query, use `list_search_direct_courts` to retrieve a clean list of supported state and agency courts. This allows your agent to dynamically adjust its search parameters based on where the litigation is occurring. You don't have to hardcode court endpoints or maintain separate API integrations for different states.

Intelligent Docket Question Answering

The `ask_docket` tool lets you ask natural language questions about specific dockets to extract precise answers without reading hundreds of pages. Your agent can run this tool to pull out key dates, motion statuses, or judge preferences. This turns dense docket sheets into clear, actionable summaries for your litigation team. If you need to build the search query first, run `smart_search` to translate plain instructions into structured search logic. This MCP tool formats the query to target specific courts or docket numbers accurately. It ensures your Google ADK agent retrieves the exact records required for your analytical pipelines.

Automated Case Tracking

The `track_case` tool is an MCP utility that registers specific dockets for real-time monitoring so your agent always has the latest filings. Once set up, any new activity on the docket triggers an alert, allowing your pipeline to update internal databases automatically. This eliminates the need for paralegals to manually log into court portals every morning. When you need to retrieve the full history of a monitored case, use `get_docket` to pull down the entire docket sheet. You can configure this tool to bypass cached records and fetch live data directly from the court. This guarantees that your enterprise analytics reflect the actual, current state of the litigation.

Setup guide

Set up Docket Alarm MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Docket Alarm tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Docket Alarm_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Docket Alarm tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You initialize the `McpToolset` class with your Vinkius HTTP URL and pass it to your `LlmAgent` constructor. The Gemini model auto-discovers the thirteen available tools, allowing it to query court records on demand.

Yes, but you must manage your queries carefully. The `search_pacer` tool charges ten cents per page of results, so you should use the test parameter during development. For broader, non-federal searches, run `search` against the cached database to minimize transactional costs.

Your agent should call `get_search_direct_args` to discover the exact parameters required by a specific state or agency court. This prevents API errors by ensuring your Google ADK pipeline sends the correct fields before executing a live search.

Yes. Your agent can use `get_complaint_summary` to extract concise bullet points or detailed overviews of newly filed lawsuits. This is ideal for feeding clean, structured case summaries directly into BigQuery or Vertex AI pipelines.

All communication with this server happens inside a secure, ephemeral V8 sandbox that isolates your API keys and search queries. Court records and PACER credentials are encrypted in transit and never stored on the host. Your proprietary search strategies and litigation targets remain completely private.

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