How to Use the Fastly MCP in Google ADK

Q: Can I feed Fastly performance data from the Google ADK into BigQuery?

Yes, your Google ADK agent can call getservicestats to retrieve raw Fastly edge metrics and then write them directly to your BigQuery tables. This lets you build real-time dashboarding pipelines using Gemini as the orchestrator.

Q: Can Gemini models trigger a global Fastly purge via Google ADK?

Yes, you can expose the purgeallcache tool to the Google ADK agent's toolset. When a content update event triggers, the Gemini model evaluates the context and executes the purge across the global Fastly CDN.

Q: Where does my Fastly configuration data go during a Google ADK run?

All Fastly configuration payloads retrieved via getservice flow through an encrypted HTTPS connection directly to your Google ADK instance. Vinkius executes the MCP code in a zero-trust, ephemeral sandbox that leaves no persistent storage trace of your Fastly edge setup.

Feed Fastly CDN performance metrics directly into Gemini models using the 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 Fastly MCP to Google ADK

Create your Vinkius account to connect Fastly 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 Fastly with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Fastly traffic patterns using Google ADK

Gemini models process massive context windows, making them perfect for looking at long-term Fastly edge trends. The Google ADK agent pulls real-time Fastly CDN usage metrics using `get_service_stats` and correlates them with your cloud data.

Domain and backend mapping via Gemini agents

Keep your Fastly edge routing configurations aligned with your Google Cloud infrastructure. The Google ADK agent calls `list_version_domains` and `list_version_backends` to map out exactly where your Fastly user traffic is heading.

Automated CDN deployments using this MCP Server

Let your Google ADK enterprise agents manage Fastly staging deployments safely. The agent uses this MCP Server to run `list_services` and find the correct Fastly target before activating the version.

Setup guide

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

Yes, your Google ADK agent can call `get_service_stats` to retrieve raw Fastly edge metrics and then write them directly to your BigQuery tables. This lets you build real-time dashboarding pipelines using Gemini as the orchestrator.

The Google ADK connects to the Vinkius-hosted MCP Server using a single secure endpoint token. Vinkius manages the underlying Fastly API token, keeping it hidden from the Gemini agent.

Yes, you can expose the `purge_all_cache` tool to the Google ADK agent's toolset. When a content update event triggers, the Gemini model evaluates the context and executes the purge across the global Fastly CDN.

Yes, the Google ADK allows you to pass a filtered list of tool names when initializing your Fastly toolset. This prevents the Gemini agent from calling high-risk Fastly tools like `delete_service` while still allowing read-only operations.

All Fastly configuration payloads retrieved via `get_service` flow through an encrypted HTTPS connection directly to your Google ADK instance. Vinkius executes the MCP code in a zero-trust, ephemeral sandbox that leaves no persistent storage trace of your Fastly edge setup.

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