How to Use the Actionstep MCP in Google ADK

Q: How do I configure the Actionstep MCP server with Google ADK?

Run pip install google-adk first. Initialize a McpToolset using StreamableHttpServerParameters with your Vinkius endpoint, then pass it to the tools array of your LlmAgent.

Q: How does Google ADK handle Actionstep matters with thousands of documents?

Gemini handles the volume natively. Your agent calls getmatterdetails and listmatternotes, feeding the massive JSON responses straight into the model. The long-context window processes the entire payload without dropping details.

Bring Actionstep data into Google ADK. Feed case files, matter notes, and billing history straight into Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Actionstep MCP to Google ADK

Create your Vinkius account to connect Actionstep 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 Actionstep with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed matter notes into Gemini

The `list_matter_notes` tool extracts every file note attached to a case. Your Google ADK agent pulls this raw text and dumps it directly into Gemini's 1-million-token context window. This means your model reads the entire history of a complex litigation at once. You skip the chunking and vector databases entirely, letting the agent cross-reference years of case history in a single pass.

Actionstep MCP Server for enterprise billing

Give your agent the `list_time_entries` tool to pull raw billable hours out of your practice management system. The agent reads the exact duration and descriptions logged by your attorneys. You route this data straight into BigQuery for analysis. Your GCP infrastructure handles the heavy lifting, comparing the pulled time entries against historical firm averages stored in your data warehouse.

Automate legal workflows

Agents execute `list_legal_tasks` and `list_action_types` to understand what your paralegals and attorneys need to do next. The tools expose the exact workflow steps configured in your system. A specialized LlmAgent reads these tasks, checks `get_matter_details` for context, and drafts initial responses. You control exactly which tools the agent sees by using the `tool_names` filter in your `McpToolset` configuration.

Setup guide

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

Run `pip install google-adk` first. Initialize a `McpToolset` using `StreamableHttpServerParameters` with your Vinkius endpoint, then pass it to the `tools` array of your `LlmAgent`.

You control the exact toolset. Pass an array of strings to the `tool_names` filter when initializing the toolset. You might expose `list_matters` to a reporting agent while hiding `create_contact` to prevent accidental database writes.

Gemini handles the volume natively. Your agent calls `get_matter_details` and `list_matter_notes`, feeding the massive JSON responses straight into the model. The long-context window processes the entire payload without dropping details.

Yes, the integration makes this simple. Your agent pulls the address book using `list_contacts`, formats the output, and writes the structured data directly to your BigQuery tables for enterprise reporting.

No. Vinkius handles the MCP connection through an isolated, stateless sandbox. Your client contacts, matter details, and billable time entries remain private. The API token grants access only for the duration of the request, leaving zero footprint behind.

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