How to Use the Helpshift MCP in Google ADK

Q: How do I configure the Helpshift MCP integration with Google ADK?

Run pip install google-adk and initialize an McpToolset using your endpoint URL. Pass that toolset directly to the tools list in your LlmAgent setup.

Q: Can Google ADK combine Helpshift data with BigQuery?

Yes. Your agent can pull ticket metadata using listissues, then query BigQuery to check the customer's lifetime value before deciding how to prioritize the response.

Q: How do I restrict which Helpshift tools the Google ADK agent can use?

Use the toolnames parameter when setting up your McpToolset. This lets you expose safe tools like listfaqs while hiding destructive ones like bulkuseraction.

Q: Why does the agent fail when calling the Helpshift issue creation tool?

The createissue tool requires a specific JSON payload containing the app ID, title, and body. Make sure Gemini is formatting the bodyjson string correctly before execution.

Feed Helpshift support queues directly into Google ADK for long-context Gemini agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Helpshift MCP to Google ADK

Create your Vinkius account to connect Helpshift 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 Helpshift with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process massive support backlogs

The `list_issues` tool feeds hundreds of open tickets directly into Gemini's massive context window. Your Google ADK agent looks at the entire queue at once, spotting trends and cross-referencing user complaints. For complex cases, the agent pulls the full thread using `get_issue_details`. It can hold the entire history of a customer's interaction in memory while querying your Vertex AI databases for a solution.

Automate ticket resolution with Google ADK

Once Gemini determines the fix, it triggers `add_issue_message` to update the user. The agent formats the response payload as a JSON string in the `body_json` parameter. It then runs `update_issue_status` to mark the ticket as resolved. If something goes wrong, you can pull `get_issue_audit_logs` to see exactly what the agent changed.

Execute fleet-wide actions via the MCP Server

When a bad deployment hits, your agent can run `bulk_user_action` to update thousands of affected user profiles simultaneously. It monitors the job via `get_bulk_task_status` while continuing to handle incoming chats. You start by running `list_registered_apps` to find the right app ID for your Helpshift environment. You can also restrict your agent to specific operations using the `tool_names` filter in your `McpToolset` config.

Setup guide

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

Run `pip install google-adk` and initialize an `McpToolset` using your endpoint URL. Pass that toolset directly to the `tools` list in your `LlmAgent` setup.

Yes. Your agent can pull ticket metadata using `list_issues`, then query BigQuery to check the customer's lifetime value before deciding how to prioritize the response.

Use the `tool_names` parameter when setting up your `McpToolset`. This lets you expose safe tools like `list_faqs` while hiding destructive ones like `bulk_user_action`.

The `create_issue` tool requires a specific JSON payload containing the app ID, title, and body. Make sure Gemini is formatting the `body_json` string correctly before execution.

The connection operates on a zero-trust architecture. When Gemini pulls sensitive support tickets or audit logs, the data passes through a secure, ephemeral V8 sandbox that retains absolutely zero state once the session ends.

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