How to Use the CourtListener MCP in Google ADK

Q: Can I limit which CourtListener tools are exposed to the Google ADK?

Yes, you can use the toolnames filter in the McpToolset configuration. This restricts your Gemini agent to specific tools like searchopinions while hiding administrative tools like listcourts.

Q: How do I run a docket search using Gemini and this toolset?

Your agent invokes searchdockets using the MCP toolset when a user asks about active litigation. The ADK translates the natural language query into structured parameters for the CourtListener API.

Connect Gemini to CourtListener via Google ADK to analyze millions of tokens of legal opinions and docket histories.

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 Google ADK

Create your Vinkius account to connect CourtListener 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 CourtListener with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-Context MCP Server Analysis in Gemini

Gemini ingests thousands of pages of legal text using the CourtListener MCP tools. The Google ADK feeds these raw opinions from `get_opinion` and `list_citations` directly into Gemini's massive 1M+ token context window, letting your agent cross-reference decades of precedent in a single prompt. This setup avoids the chunking errors common with traditional vector databases. You get high-fidelity legal reasoning across complete judicial texts instead of disjointed snippets.

BigQuery Legal Data Enrichment

Your agent joins internal corporate litigation tables in BigQuery with live docket data pulled via `search_dockets`. Google ADK coordinates this data flow, letting you enrich your historical records with real-time court updates. You can automatically flag active lawsuits involving your suppliers. The agent runs the search, compares the parties, and updates your BigQuery datasets without human intervention.

Judicial Profiling at Enterprise Scale

Google ADK lets your agent build exhaustive profiles of presiding judges by calling `get_judge` and `list_financial_disclosures`. The agent extracts financial interests and career histories to help your litigation team assess potential bias. Because this runs on Google Cloud infrastructure, you can scale this profiling across hundreds of judges simultaneously. Your team receives structured briefs before entering the courtroom.

Setup guide

Set up CourtListener 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 CourtListener 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="CourtListener_agent",
    model="gemini-2.0-flash",
    instruction="You have access to CourtListener 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 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 Google ADK

Yes, you can use the `tool_names` filter in the `McpToolset` configuration. This restricts your Gemini agent to specific tools like `search_opinions` while hiding administrative tools like `list_courts`.

Gemini's long-context window natively accepts the full text returned by `get_opinion`. The ADK passes this raw legal data directly without requiring complex RAG pipelines.

Yes, Vinkius provides an HTTP endpoint that you pass to the `StreamableHttpServerParameters` in the ADK. This establishes a secure, remote connection to the CourtListener MCP Server.

Your agent invokes `search_dockets` using the MCP toolset when a user asks about active litigation. The ADK translates the natural language query into structured parameters for the CourtListener API.

Your docket searches and retrieved judge bios remain within your secure Google Cloud perimeter. Vinkius processes these requests through a zero-trust, ephemeral V8 isolate that retains no logs or data after execution.

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