How to Use the Knack MCP in Google ADK

Q: Does the Google ADK support filtering Knack records?

Yes. The agent uses the searchrecords tool by constructing a JSON string that matches the Knack Filter format.

Q: Can I limit which Knack tools my Google ADK agent sees?

You absolutely can. Use the toolnames filter in the McpToolset configuration to expose only safe operations like listrecords, hiding destructive ones like deleterecord.

Give your Google ADK agents full CRUD access to Knack to sync records, map schemas, and feed BigQuery pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Knack MCP to Google ADK

Create your Vinkius account to connect Knack 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 Knack with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Navigate complex database structures

The `list_account_applications` tool verifies your access and pulls the exact application IDs your Google ADK agent needs. From there, it calls `list_objects` to map out the entire application structure. Gemini has a massive context window, meaning you can dump the entire database structure into memory at once. Your agent holds the complete map. It cross-references tables and plans complex data migrations without losing track of the object keys.

Push updates via the Knack MCP Server

The `update_record` tool modifies existing rows by sending partial JSON payloads through the Knack MCP Server. If your agent detects a discrepancy between a Vertex AI output and your database, it patches the exact field instantly. When you need to log new events, `create_record` inserts fresh rows. You just pass the JSON string with the correct field keys, and the agent handles the HTTP transaction natively.

Extract and filter specific data sets

The `search_records` tool takes Knack Filter JSON arrays to isolate specific rows based on complex conditions. Your agent pulls targeted subsets of data to feed into downstream Google Cloud analytics tools. For broader data extraction, `list_records` grabs entire pages of an object's contents. You feed this raw data directly into BigQuery or use Gemini to summarize thousands of rows of customer feedback in a single pass.

Setup guide

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

Instantiate McpToolset using StreamableHttpServerParameters with your server URL. Pass that toolset into the tools array of your LlmAgent.

Yes. The agent uses the search_records tool by constructing a JSON string that matches the Knack Filter format.

You absolutely can. Use the tool_names filter in the McpToolset configuration to expose only safe operations like list_records, hiding destructive ones like delete_record.

Typical reads execute in under 200 milliseconds. Complex filtered searches might take slightly longer depending on the size of your database and the indexing on those specific fields.

The MCP Server transmits your application schemas and individual record payloads straight to your Google Cloud environment. We do not cache your database tables or log the contents of your JSON write operations.

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