How to Use the Freshsuccess MCP in Google ADK

Q: How do I configure the Freshsuccess MCP Server tools inside a Google ADK agent?

Use the McpToolset class and pass your Vinkius HTTP URL in the server parameters. Then, pass this toolset object into the LlmAgent constructor to give Gemini access to tools like listcsaccounts.

Q: How do I verify that my Gemini agent can reach the customer database?

Have your agent call checkapistatus first. This tool returns a simple status check, confirming that your credentials are valid and the Vinkius connection is active before you run complex workflows.

Run enterprise customer health analysis in Google ADK using Gemini models and Freshsuccess telemetry.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshsuccess MCP to Google ADK

Create your Vinkius account to connect Freshsuccess 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 Freshsuccess with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise account analysis with Google ADK

By calling `list_cs_accounts` alongside your BigQuery datasets, you can analyze massive accounts directly inside Gemini's long-context window. Your agent cross-references database records against active customer status. This lets you spot churn risks across thousands of accounts simultaneously. The Google ADK handles the connection to the Freshsuccess MCP Server using the `McpToolset` class. This exposes tools like `get_account_health` directly to Gemini, allowing the model to reason over complex user behaviors without hitting token limits.

Automated task creation from usage alerts

Monitoring usage drops via `list_cs_alerts` allows your agent to identify accounts that need immediate attention. It then runs `upsert_cs_user` or creates an action item via `list_cs_tasks` to ensure a customer success manager follows up. This setup runs natively on Google Cloud infrastructure. You can run these agents as headless workers that process alerts in the background, keeping your CRM updated without human developers writing custom glue code.

Custom metric logging from cloud pipelines

Writing telemetry data with `post_metric_value` sends application metrics directly into your customer success dashboard. Your agent can process raw application logs and log usage trends. This ensures your customer health scores reflect real, up-to-the-minute activity. You can restrict the agent's capabilities using the `tool_names` filter in the ADK. This ensures the pipeline agent can only execute `list_custom_metrics` and write operations, preventing it from reading sensitive account lists.

Setup guide

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

Use the `McpToolset` class and pass your Vinkius HTTP URL in the server parameters. Then, pass this toolset object into the `LlmAgent` constructor to give Gemini access to tools like `list_cs_accounts`.

Yes. The ADK supports both Stdio and HTTP transports. While HTTP is standard for hosted Vinkius endpoints, you can run a local proxy that communicates with the server via standard input/output.

The ADK relies on the underlying Gemini model to handle tool execution. If tools like `get_account_health` return rate limit errors, you should implement backoff logic in your agent's execution loop to prevent failures.

Have your agent call `check_api_status` first. This tool returns a simple status check, confirming that your credentials are valid and the Vinkius connection is active before you run complex workflows.

Yes. Your telemetry data is transmitted via the secure MCP gateway directly to the Vinkius gateway, which runs in an isolated V8 sandbox. This prevents raw database metrics or API keys from being stored or used for model training by external LLM engines.

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