How to Use the Knackly MCP in Google ADK

Q: How do I initialize Knackly inside Google ADK?

Install google-adk and configure a McpToolset using StreamableHttpServerParameters. Pass this toolset to your LlmAgent initialization.

Q: Can Google ADK filter which Knackly tools the agent sees?

Yes. You can use the toolnames filter in the toolset configuration. This restricts the agent to specific actions, like only allowing listgenerateddocuments for a read-only auditor.

Q: How does Knackly work with Google ADK's long context?

The agent can fetch hundreds of template definitions via listdatamodels and hold them in memory. It then evaluates which template fits your BigQuery data before drafting.

Give Google ADK agents the power to draft conditional legal documents through the Knackly MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Knackly MCP to Google ADK

Create your Vinkius account to connect Knackly 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 Knackly with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query workspaces and catalogs

`list_workspaces` pulls your active Knackly environments directly into your Gemini agent context. The agent scans the available directories and uses `list_catalogs` to locate the correct template repository for the task. Google ADK handles massive context windows. You can feed your agent an entire BigQuery dataset of client records, and it will map those rows to the available workspaces without dropping details.

Map models and create records

`list_data_models` exposes the exact schema your smart templates require. Once the agent understands the conditional logic, it triggers `create_data_record` to push new business data into the assembly queue. This MCP Server works perfectly with Vertex AI pipelines. Your Gemini agent reads the required fields, extracts the matching data from your enterprise storage, and fires the creation payload in one fluid motion.

Track documents with Google ADK

`list_generated_documents` retrieves the status of your automated files. The agent checks this endpoint to confirm the final legal agreements compiled successfully. You can also audit your notification pipelines using `list_webhooks` and `get_record_details`. If an enterprise agent needs to verify that a specific record triggered a downstream event, it pulls the exact configuration from the server.

Setup guide

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

Install `google-adk` and configure a `McpToolset` using `StreamableHttpServerParameters`. Pass this toolset to your `LlmAgent` initialization.

Yes. You can use the `tool_names` filter in the toolset configuration. This restricts the agent to specific actions, like only allowing `list_generated_documents` for a read-only auditor.

The agent can fetch hundreds of template definitions via `list_data_models` and hold them in memory. It then evaluates which template fits your BigQuery data before drafting.

Yes. The toolset natively supports HTTP connections. You just provide your endpoint token to authenticate the requests.

The system routes your business entity data through an ephemeral, zero-trust connection. Vinkius drops the instance the moment the document assembly request completes, leaving no cached copies 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