How to Use the Freshworks MCP in Google ADK

Q: How do I connect the Google ADK to the Freshworks MCP server?

Instantiate the McpToolset class and provide it with the Vinkius server URL inside StreamableHttpServerParameters. Then, you just pass that toolset into your LlmAgent constructor and it's ready to go.

Q: Can my Google ADK agent work with both Freshworks sales and support data?

Absolutely. The agent can call tools like listdeals from the sales module and listtickets from the support module in the same session. This gives it a complete view of a customer's status.

Q: Is it possible to run a Google ADK agent with Freshworks tools in a CI/CD pipeline?

Yes, it's designed for it. The ADK supports a Stdio transport in addition to HTTP, which is made for running agents in headless environments like a CI/CD runner or a serverless function.

Q: How can I correlate Freshworks contact data using the Google ADK?

Your agent can fetch data from both listcrmcontacts and listhelpdeskcontacts. You can then implement logic within your agent's code to match records based on email or other shared fields.

Q: What happens to our Freshworks deal and ticket data when accessed by a Google ADK agent?

The data, such as deal values from listdeals and ticket descriptions from getticket, is streamed from the Vinkius MCP server to your agent for processing. It is not stored by the server, which runs in a zero-trust, ephemeral sandbox to protect your operational data.

Connect Freshworks to your Google Cloud workflow. Let Gemini agents act on your sales and support data with Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshworks MCP to Google ADK

Create your Vinkius account to connect Freshworks 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 Freshworks with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Freshworks, Analyze in BigQuery

Use a Gemini agent to pull your entire deal pipeline from Freshworks with `list_deals`. The agent can then load that data directly into a BigQuery table for long-term analysis, all in one operation. This closes the loop between live operations and business intelligence. You can correlate ticket trends from `list_tickets` with account health from `list_accounts` without building and maintaining a separate ETL pipeline.

Long-Context Reasoning on Tickets

Gemini's large context window is perfect for complex support issues. Your agent can pull a customer's entire ticket history using `list_tickets` and `list_helpdesk_contacts` and hold it all in memory to see the big picture. This means it can spot patterns that a human might miss. The agent can see the connection between three seemingly unrelated tickets and a deal that's about to churn, all by reasoning over the raw data from the Freshworks tools.

Filter Tools for Your Google ADK Agent

You don't have to expose all nine Freshworks tools to every agent. The Google ADK `McpToolset` lets you pass a `tool_names` filter to restrict access to only what's needed for the job. For example, create a support-only agent that can only see `get_ticket` and `list_agents`. Then build a separate sales agent that only has permission to use `list_deals` and `list_crm_contacts`. It's a simple way to enforce least-privilege access.

Setup guide

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

Instantiate the `McpToolset` class and provide it with the Vinkius server URL inside `StreamableHttpServerParameters`. Then, you just pass that toolset into your `LlmAgent` constructor and it's ready to go.

Absolutely. The agent can call tools like `list_deals` from the sales module and `list_tickets` from the support module in the same session. This gives it a complete view of a customer's status.

Yes, it's designed for it. The ADK supports a `Stdio` transport in addition to HTTP, which is made for running agents in headless environments like a CI/CD runner or a serverless function.

Your agent can fetch data from both `list_crm_contacts` and `list_helpdesk_contacts`. You can then implement logic within your agent's code to match records based on email or other shared fields.

The data, such as deal values from `list_deals` and ticket descriptions from `get_ticket`, is streamed from the Vinkius MCP server to your agent for processing. It is not stored by the server, which runs in a zero-trust, ephemeral sandbox to protect your operational data.

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