How to Use the Froged MCP in Google ADK

Q: Can I restrict which Froged tools Google ADK exposes?

Yes. Use the toolnames array when configuring the toolset. This lets you expose getcontactdetails while hiding destructive tools from specific agents.

Q: Does Froged work with Gemini's long context window?

Yes. You can pull massive arrays from listcscontacts and feed them into Gemini. The model easily processes thousands of contact records in a single prompt.

Q: How do I check if the Froged API is down?

Have your agent run verifyapistatus before starting a complex workflow. If the API is unreachable, the agent can pause operations instead of failing mid-task.

Connect Froged to Google ADK to build enterprise Gemini agents that manage support tickets and user events.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Froged MCP to Google ADK

Create your Vinkius account to connect Froged 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 Froged with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Froged Chats into Gemini

This MCP Server connects `list_support_conversations` straight to your Google ADK environment. Gemini models have massive context windows, so your agent can ingest months of historical chat logs in seconds. It reads the full context before typing a single word. Once the agent decides on a fix, it fires `send_chat_message` to update the user. If the user asks about a specific feature, the agent pulls `list_kb_articles` and summarizes the exact steps. You get fast, accurate support without leaving Google Cloud.

Unify Behavioral Events with BigQuery

Your agent pulls raw user activity using `list_behavioral_events`. It sees exactly where a customer clicked before they got stuck and opened a ticket. You do not have to guess what went wrong. Because you run this through Google ADK, your agent can cross-reference these Froged events with your existing BigQuery datasets. If a customer hits a known bug, the agent logs it via `track_custom_event` and alerts your engineering team via Vertex AI pipelines.

Filter MCP Server Tools by Agent

You can restrict which tools specific agents access using the tool_names filter in Google ADK. Your Tier 1 support agent might only get `get_chat_details` and `list_kb_articles` to answer basic questions safely. Meanwhile, your account management agent gets `upsert_contact` and `list_marketing_campaigns`. This prevents a basic support bot from accidentally altering customer metadata or launching a campaign. You keep strict boundaries around what each LLM can actually execute.

Setup guide

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

Install google-adk. Create a McpToolset using StreamableHttpServerParameters with your Vinkius URL. Pass that toolset directly to your LlmAgent configuration.

Yes. Use the tool_names array when configuring the toolset. This lets you expose get_contact_details while hiding destructive tools from specific agents.

Yes. You can pull massive arrays from list_cs_contacts and feed them into Gemini. The model easily processes thousands of contact records in a single prompt.

Have your agent run verify_api_status before starting a complex workflow. If the API is unreachable, the agent can pause operations instead of failing mid-task.

The MCP integration touches behavioral event logs and marketing campaign metrics. Vinkius enforces a zero-trust architecture where every connection is completely stateless. Your Google Cloud environment holds the keys, and we never persist your behavioral 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