How to Use the HelpCrunch MCP in Google ADK

Q: How do I initialize the HelpCrunch MCP tools in Google ADK?

Install google-adk and set up a McpToolset using your server URL. Pass this toolset to your LlmAgent initialization. Gemini will automatically map the tools to its reasoning engine.

Q: Can Google ADK filter which HelpCrunch tools are exposed?

You can restrict access using the toolnames parameter in the ADK. If you only want Gemini to read data, you just expose listchats and getchatdetails while hiding the write tools.

Q: Does this setup work for searching historical HelpCrunch conversations with Google ADK?

Yes. The searchchats tool accepts complex JSON filters. Gemini constructs these filters based on your natural language prompts to dig up past interactions instantly.

Q: Is customer profile data exposed during these operations?

The system handles names, emails, and internal IDs via getcustomerdetails. We route all requests through a zero-trust architecture where this MCP Server drops all data from memory after execution, guaranteeing your customer information remains strictly in transit.

Connect Gemini to HelpCrunch using Google ADK to analyze massive chat histories and automate your support operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HelpCrunch MCP to Google ADK

Create your Vinkius account to connect HelpCrunch 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 HelpCrunch with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed chat history to this MCP Server

The `list_chat_messages` and `list_chats` tools pull raw conversation data directly into Gemini's massive context window. Your agent ingests thousands of messages to spot recurring bugs before your engineering team even notices them. You pipe this data straight into BigQuery for long-term storage. The Google ADK handles the flow, moving support interactions from isolated silos into your broader cloud infrastructure.

Resolve tickets with enterprise context

The `send_message` tool allows your Gemini agent to reply to active conversations. It accesses your Vertex AI knowledge bases, so the agent answers highly technical questions that standard MCP bots fail to understand. Before replying, the agent checks `get_customer_details` to understand who it is talking to. It tailors the response based on the customer's history and account size, ensuring enterprise clients get the exact answers they need.

Manage support routing autonomously

The `update_chat_assignee` tool shifts conversations to specific human agents when Gemini detects frustration. It pairs with `list_departments` to find the right team, keeping your escalation paths strictly enforced. Your agent also keeps the workspace organized by calling `add_customer_tag` based on the conversation topic. It then uses `update_chat_status` to close out resolved issues, reducing the morning backlog for your human staff.

Setup guide

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

Install `google-adk` and set up a `McpToolset` using your server URL. Pass this toolset to your `LlmAgent` initialization. Gemini will automatically map the tools to its reasoning engine.

You can restrict access using the `tool_names` parameter in the ADK. If you only want Gemini to read data, you just expose `list_chats` and `get_chat_details` while hiding the write tools.

Yes. The `search_chats` tool accepts complex JSON filters. Gemini constructs these filters based on your natural language prompts to dig up past interactions instantly.

The MCP protocol standardizes the tool calls, but you should implement retry logic within your Google Cloud architecture. The server returns standard HTTP status codes when you hit the endpoint limits.

The system handles names, emails, and internal IDs via `get_customer_details`. We route all requests through a zero-trust architecture where this MCP Server drops all data from memory after execution, guaranteeing your customer information remains strictly in transit.

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