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

Run multi-step LangChain pipelines to clear KeyCDN edge caches and manage pull zones based on live traffic reports.

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 LangChain

Create your Vinkius account to connect KeyCDN (Content Delivery Network) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Clear specific assets with LangChain

Your LangChain agents can immediately check KeyCDN edge states and wipe stale assets without manual work. Triggering `purge_specific_url` inside a LangChain ReAct loop lets your agent verify an asset update and wipe the KeyCDN edge cache in one continuous chain. Use LangSmith to track every KeyCDN cache-clearing decision your LangChain agent makes. If a KeyCDN file update fails to propagate, the LangChain agent sees the error, logs the latency, and can fall back to `purge_zone_cache_all` to keep content fresh.

Provision KeyCDN resources dynamically

Build LangChain chains that spin up brand new KeyCDN edge nodes when deployment pipelines finish. The MCP Server fires `add_pull_zone` to spin up a new KeyCDN endpoint, then maps your custom domain instantly within your LangChain pipeline. Every step of the KeyCDN configuration is fully observable in LangSmith. You can feed the output of your KeyCDN zone creation directly into your LangChain DNS tools, making the entire setup process completely hands-off.

Automate KeyCDN bandwidth routing

Pull live KeyCDN metrics to make smart routing decisions in your LangChain chain. By invoking `list_traffic_reports`, your LangChain agent reads current KeyCDN bandwidth consumption and determines if a zone needs configuration tweaks. This turns static KeyCDN monitoring into an active, self-healing network loop using LangChain. The LangChain agent parses the raw KeyCDN traffic data, checks it against your limits, and alerts your team before bandwidth spikes cost you a fortune.

Setup guide

Set up KeyCDN (Content Delivery Network) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes KeyCDN (Content Delivery Network) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "keycdn-content-delivery-network-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent KeyCDN (Content Delivery Network) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

It exposes KeyCDN API endpoints as tools directly to your LangChain agent. You register the MCP Server, and your ReAct agents can call `purge_specific_url` or `list_zones` during active runs.

Yes, every single tool execution is fully logged. You will see exact input parameters for `purge_zone_cache_all` and the API response latency inside your LangSmith dashboard.

You should configure your LangChain runnable with a retry helper. If a tool like `add_zone_alias` hits KeyCDN rate limits, the chain backs off and retries automatically.

Absolutely. The agent uses the MCP connection to find all active zones, loop through them, and execute bulk operations like `get_zone` sequentially in a single execution path.

Vinkius runs the MCP Server in an isolated V8 sandbox, meaning your API tokens are never exposed. It only accesses KeyCDN zone configurations and traffic logs during active tool executions, discarding all session memory immediately after the run.

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