How to Use the Helpjuice MCP in Google ADK

Q: How do I connect the Google ADK to my Helpjuice account?

You'll use the McpToolset and provide your Vinkius server URL in the StreamableHttpServerParameters. Pass the resulting toolset into the tools list when creating your LlmAgent.

Q: What's the best way to keep our Helpjuice KB fresh using the Google ADK?

Set up a recurring agent task. It can use getarticlestats to find articles with low views or high downvotes and automatically flag them for review. For simple fixes, it could even be authorized to call updatearticle directly.

Q: Does this MCP server support filtering which Helpjuice tools are exposed to the Google ADK?

Yes. When you create the McpToolset in your Google ADK code, you can pass a toolnames list to explicitly define which of the 12 Helpjuice tools you want to expose to the agent.

Connect Google ADK to your Helpjuice knowledge base. Analyze KB performance with BigQuery and build long-context support agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Helpjuice MCP to Google ADK

Create your Vinkius account to connect Helpjuice 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 Helpjuice with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Your Entire KB at Scale

Use an agent to call `list_articles` and feed the content into a Gemini model with a 1M+ token context window. Your agent can read and reason about your entire knowledge base at once, finding inconsistencies or outdated branding that spans hundreds of articles. Combine this with data from `get_search_trends`. Your Google ADK agent can cross-reference what users are looking for against the full text of your documentation to spot conceptual gaps, not just keyword misses.

Sync Helpjuice Analytics to BigQuery

Build a Google ADK agent that runs on a schedule. Have it iterate through your articles, call `get_article_stats` on each one, and pipe the engagement data directly into a BigQuery table. Now you can build Looker dashboards on real KB performance. Correlate `downvote_article` events with recent product releases or track how `get_search_trends` change over time, all within your existing Google Cloud environment.

Enterprise Support on Google Cloud

The `McpToolset` makes it simple to give your Gemini-powered agent access to your Helpjuice instance. Your agent can `search_kb` for answers, and if it finds nothing, it can use other Google Cloud tools to create a Jira ticket or draft an article with `create_article`. Because this is an MCP server, authentication is already handled. You just point the Google ADK to the Vinkius endpoint URL and the tools are ready. You can focus on your agent's logic, not the plumbing.

Setup guide

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

You'll use the `McpToolset` and provide your Vinkius server URL in the `StreamableHttpServerParameters`. Pass the resulting toolset into the `tools` list when creating your `LlmAgent`.

Absolutely. The agent can pull search data from Helpjuice using `get_search_trends`, then use a different toolset to query BigQuery. This lets you build agents that work across your different data silos.

Set up a recurring agent task. It can use `get_article_stats` to find articles with low views or high downvotes and automatically flag them for review. For simple fixes, it could even be authorized to call `update_article` directly.

Yes. When you create the `McpToolset` in your Google ADK code, you can pass a `tool_names` list to explicitly define which of the 12 Helpjuice tools you want to expose to the agent.

The server processes Helpjuice article text and user engagement stats—like search terms from `get_search_trends`—in a temporary, zero-trust environment. All communication is TLS-encrypted, and your server token is stored using hardened security practices.

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