How to Use the Fibery MCP in Google ADK

Q: How do I initialize the Fibery MCP Server inside the Google ADK?

Use the McpToolset class from the Google ADK and point it to your Vinkius HTTP transport URL. Pass this toolset directly into your Google ADK LlmAgent initialization to expose the 11 Fibery workspace tools to Gemini.

Q: Can I combine my BigQuery tools and Fibery tools in one Google ADK agent?

You can load multiple toolsets into a single Google ADK LlmAgent instance. This lets your Gemini agent query your BigQuery data warehouse and immediately update a Fibery entity based on those insights.

Connect Gemini to Fibery using the Google ADK to analyze workspace databases alongside your BigQuery data warehouses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fibery MCP to Google ADK

Create your Vinkius account to connect Fibery 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 Fibery with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-Context Fibery Analysis with Google ADK

Gemini's massive context window inside the Google ADK lets you feed entire Fibery workspaces into your prompt. This MCP Server lets your Google ADK agent run `get_schema` and `query_entities` to ingest raw Fibery databases for deep reasoning. Instead of making dozens of small API calls, your Google ADK agent pulls entire tables of Fibery entities and maps their connections in a single prompt. This approach lets Gemini find patterns across your entire Fibery workspace using the Google ADK that smaller setups miss.

Enterprise Fibery and BigQuery Sync via Google ADK

You can connect your operational Fibery workspace directly to your analytical BigQuery data warehouse using the Google ADK. Your Google ADK agent reads Fibery records via `query_entities` and compares them to your enterprise tables in BigQuery. When the Google ADK agent finds a mismatch, it uses `update_entity` or `create_entity` to fix the Fibery records. This keeps your Fibery tracking data perfectly aligned with your actual BigQuery metrics via the Google ADK.

Granular Google ADK Tool Access for Fibery

Enterprise Google ADK deployments require strict boundaries on what your agent can do in Fibery. The Google ADK lets you pass an optional `tool_names` filter to restrict which Fibery tools are exposed to the Gemini model. You can configure a Google ADK agent that only reads data by exposing `get_entity` and `list_users` while blocking destructive Fibery tools like `delete_entity`. This ensures your Fibery workspace remains secure even during autonomous Google ADK agent runs.

Setup guide

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

Use the `McpToolset` class from the Google ADK and point it to your Vinkius HTTP transport URL. Pass this toolset directly into your Google ADK `LlmAgent` initialization to expose the 11 Fibery workspace tools to Gemini.

Yes, Gemini's million-token context window inside the Google ADK is perfect for processing large payloads returned by Fibery's `query_entities`. The Gemini model can analyze thousands of Fibery workspace items without running out of memory.

Yes, the Google ADK supports both transport protocols. When running on Vinkius, you will use the streamable HTTP server parameters to connect your Google ADK agent to the managed Fibery MCP Server.

You can load multiple toolsets into a single Google ADK `LlmAgent` instance. This lets your Gemini agent query your BigQuery data warehouse and immediately update a Fibery entity based on those insights.

Your Fibery API tokens and workspace schemas are processed entirely in memory within an isolated V8 sandbox before reaching the Google ADK. We never store your Fibery entity details, user lists, or comment text, ensuring strict compliance with enterprise data policies.

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