How to Use the LEAP Legal MCP in Google ADK

Q: Can I use Google ADK to write new contacts back to LEAP Legal?

Yes, your agent can write contacts using createnewcard if you expose that tool to the toolset. You define the server parameters in Python and pass them to your agent. This enables automated contact creation during client onboarding.

Q: How does Google ADK handle large document lists from LEAP Legal?

The ADK feeds the output of getmatterdocumentsonly directly into Gemini's long-context window. This allows the model to analyze hundreds of legal documents simultaneously. You avoid the need for complex chunking strategies or vector databases.

Connect Gemini models to LEAP Legal via Google ADK using this MCP Server to analyze court documents and update active matter files.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LEAP Legal MCP to Google ADK

Create your Vinkius account to connect LEAP Legal 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 LEAP Legal with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect Gemini to legal cases using this MCP Server

`get_matter_details` retrieves case files so your Google ADK agent can analyze them using Gemini's million-token context window. You initialize the connection by passing the MCP Server parameters to your `LlmAgent` tool list. This lets the agent query case details alongside your enterprise BigQuery datasets. Your agent inspects the case history to identify outstanding tasks. It pulls linked contacts using `get_matter_linked_cards` to map out the parties involved. You get deep reasoning across your entire legal catalog without hitting token limits.

Filtered tool access for enterprise security

`list_legal_matter_types` fetches the valid matter categories for your target country using the Google ADK configuration. You restrict access to sensitive tools by passing a specific tool name list to your `StreamableHttpServerParameters`. This ensures your agent only calls approved endpoints during execution. Your system prevents unauthorized changes to active matters. The agent checks valid categories before attempting to create new entries. This matching step keeps your legal database clean and compliant with local jurisdiction rules.

Automated correspondence analysis

`get_matter_correspondence` pulls emails, documents, and appointments into your Gemini reasoning loop. The Google ADK agent processes this timeline to build a chronologically ordered case summary. You can cross-reference this data with your internal Vertex AI search indexes. Attorneys review case history without opening multiple application windows. Your agent extracts key dates from the correspondence and flags upcoming deadlines. The integration runs on secure Google Cloud infrastructure to protect sensitive client communications.

Setup guide

Set up LEAP Legal 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 LEAP Legal 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="LEAP Legal_agent",
    model="gemini-2.0-flash",
    instruction="You have access to LEAP Legal 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 LEAP Legal. 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 LEAP Legal 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 LEAP Legal MCP in Google ADK

Yes, your agent can write contacts using `create_new_card` if you expose that tool to the toolset. You define the server parameters in Python and pass them to your agent. This enables automated contact creation during client onboarding.

You run the server via HTTP transport by pointing the ADK parameter block to your Vinkius endpoint. The SDK connects to the hosted MCP Server securely. Vinkius manages the server lifecycle, so your Cloud Run or GKE instances stay lightweight.

The ADK feeds the output of `get_matter_documents_only` directly into Gemini's long-context window. This allows the model to analyze hundreds of legal documents simultaneously. You avoid the need for complex chunking strategies or vector databases.

Yes, you can write a custom agent that queries your BigQuery billing tables and matches them with matters retrieved via `list_matters`. The agent uses the combined data to draft accurate invoice summaries. This unifies your enterprise data with your active legal files.

Your matter details, documents, and contacts are transmitted over TLS directly to your isolated Google Cloud environment. Vinkius runs the MCP Server in zero-trust, ephemeral sandboxes that never persist your legal files. No third party can access your case data or contact records.

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