How to Use the KeyCDN (Content Delivery Network) MCP in Google ADK

Q: How do I set up KeyCDN (Content Delivery Network) with Google ADK?

Install google-adk via pip. Initialize a McpToolset using StreamableHttpServerParameters with your Vinkius URL, then pass it to your LlmAgent under the tools argument.

Q: Can I restrict which KeyCDN (Content Delivery Network) tools the Google ADK agent sees through the MCP connection?

Yes. Use the toolnames filter in your toolset configuration. You can expose purgespecificurl while hiding deletezone to prevent destructive actions.

Q: How do I provision new edge resources with KeyCDN (Content Delivery Network) and Google ADK?

Your Gemini agent calls addpullzone to create the base origin connection. It follows up with addzonealias to attach custom domains based on your deployment specifications.

Connect KeyCDN edge infrastructure directly to your Google ADK agents using this managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KeyCDN (Content Delivery Network) MCP to Google ADK

Create your Vinkius account to connect KeyCDN (Content Delivery Network) 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 KeyCDN (Content Delivery Network) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Edge Management via MCP Server

Gemini's massive context window means you can feed it your entire infrastructure state. By hooking up this server, your agent runs `list_zones` and `list_zone_aliases` to map every active KeyCDN endpoint. It cross-references those configurations against your BigQuery logs to find unused pull zones. When it finds stale infrastructure, the agent acts immediately. It triggers `delete_zone` to instantly revoke wildcard subdomains and drop proxy connections. The agent handles the cleanup autonomously without you touching the KeyCDN portal.

Targeted Cache Invalidation

Serving stale content hurts user experience and damages campaigns. When your Vertex AI pipelines push new models or static assets, the agent immediately fires `purge_specific_url`. It targets exact paths so your origin avoids getting hammered by sudden cache misses. For massive site overhauls, the agent falls back to `purge_zone_cache_all`. It clears the whole pull zone in one shot. You dictate the logic, and Gemini figures out which purge method fits the deployment size based on your prompt instructions.

Traffic Reporting & Analytics

Your agent needs visibility into edge performance to make routing decisions. It calls `list_traffic_reports` to pull raw bandwidth consumption metrics straight from the CDN. The agent structures this data for immediate analysis. Because you operate in the Google ecosystem, the agent pipes those bandwidth numbers straight into BigQuery. It uses `get_zone` to attach configuration details to the traffic rows. You get a complete, queryable view of your edge spend.

Setup guide

Set up KeyCDN (Content Delivery Network) 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 KeyCDN (Content Delivery Network) 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="KeyCDN (Content Delivery Network)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to KeyCDN (Content Delivery Network) 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 KeyCDN. 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 KeyCDN (Content Delivery Network) 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 KeyCDN (Content Delivery Network) MCP in Google ADK

Install `google-adk` via pip. Initialize a `McpToolset` using `StreamableHttpServerParameters` with your Vinkius URL, then pass it to your `LlmAgent` under the `tools` argument.

Yes. Use the `tool_names` filter in your toolset configuration. You can expose `purge_specific_url` while hiding `delete_zone` to prevent destructive actions.

The framework handles asynchronous tool execution natively. Your agent can fire multiple `purge_specific_url` requests simultaneously when analyzing large Vertex AI update batches.

Your Gemini agent calls `add_pull_zone` to create the base origin connection. It follows up with `add_zone_alias` to attach custom domains based on your deployment specifications.

The server only reads bandwidth consumption stats and zone configurations. Vinkius runs the connection in an ephemeral container, meaning your edge metrics never persist outside your Google Cloud 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