How to Use the Freshservice MCP in Google ADK

Q: How do I use Freshservice tools inside a Google ADK agent?

Instantiate an McpToolset with your Vinkius server URL and pass it to the tools parameter of your LlmAgent. The ADK handles the communication, making Freshservice tools like listitsmtickets available to your Gemini model.

Q: Can I build a Google ADK agent that only reads from Freshservice?

Yes, easily. When you create the McpToolset for Freshservice, use the toolnames filter to specify a list of read-only tools like getticketdetails and listitassets. This prevents the agent from making any changes.

Q: Does the Google ADK support streaming from the Freshservice MCP Server?

Yes. The McpToolset can be configured with StreamableHttpServerParameters to handle streaming responses. This is useful for tools that might return a lot of data, like listitsmtickets on a busy Monday morning.

Connect Freshservice to your Google Cloud data and build enterprise agents 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 Freshservice MCP to Google ADK

Create your Vinkius account to connect Freshservice 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 Freshservice with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn BigQuery Insights Into Action

Your data is in BigQuery, but your IT team lives in Freshservice. This MCP Server bridges that gap. Use a Gemini agent to analyze asset health data in a table, then have it automatically use `create_itsm_ticket` when it finds a failing drive. The Google ADK makes this direct. Your agent can pull a list of devices with `list_it_assets` from Freshservice, cross-reference them with telemetry data in BigQuery, and then use `get_asset_details` to confirm the model before logging the incident.

Manage IT Operations at Scale

The long-context window of Gemini models means your agent can hold more information at once. It can take in the entire output of `list_itsm_tickets` and `list_it_problems` to identify patterns that a human staring at a dashboard might miss. Imagine an agent that reads through hundreds of change requests from `list_change_requests`, correlates them with new problem reports, and flags a risky deployment for review. That's what you can build when your agent has enough context to see the whole picture.

Build Agents on Google Cloud with this MCP Server

This MCP Server fits right into your existing Google Cloud workflow. Define your Freshservice connection using `McpToolset` and pass it to your `LlmAgent`. There's no need to run a separate service or manage complex authentication. You can even control which tools are exposed. Use the `tool_names` filter to create a specialized agent that can, for example, only read ticket data with `get_ticket_details` but can't create new ones. It’s granular control for enterprise environments.

Setup guide

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

Instantiate an `McpToolset` with your Vinkius server URL and pass it to the `tools` parameter of your `LlmAgent`. The ADK handles the communication, making Freshservice tools like `list_itsm_tickets` available to your Gemini model.

Yes, easily. When you create the `McpToolset` for Freshservice, use the `tool_names` filter to specify a list of read-only tools like `get_ticket_details` and `list_it_assets`. This prevents the agent from making any changes.

Yes. The `McpToolset` can be configured with `StreamableHttpServerParameters` to handle streaming responses. This is useful for tools that might return a lot of data, like `list_itsm_tickets` on a busy Monday morning.

You don't have to worry about it. Your Vinkius endpoint URL includes a token that authenticates your agent with the managed server. The Google ADK just needs that one URL.

The agent can access whatever data the 12 tools provide—that includes ticket contents, asset information, and user details. Security is handled by Vinkius's zero-trust model, where each request is authenticated and run in a temporary, isolated environment.

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