How to Use the Fastly MCP in OpenAI Agents SDK

Q: How does Fastly cache purging work inside the OpenAI Agents SDK?

Your agent calls the purgeallcache tool directly when a content update occurs. The OpenAI Agents SDK handles the asynchronous execution and returns the Fastly API response status to the agent loop. You can trace this entire execution flow in your OpenAI dashboard.

Deploy Fastly CDN updates and purge edge caches safely using the OpenAI Agents SDK guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Fastly to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate and deploy Fastly versions via OpenAI Agents SDK

OpenAI agents can deploy Fastly edge configurations directly within your Python runtime. Using the OpenAI Agents SDK, your agent calls `list_service_versions` to find your current draft and runs checks before executing `activate_service_version` to make it live.

Targeted cache clearing and origin auditing

When your backend changes, the OpenAI Agents SDK keeps your Fastly edge in sync. By calling `list_version_backends`, it queries origin details and triggers a clean slate across the Fastly global network with `purge_all_cache` when deployments finish.

Automated CDN provisioning with strict guardrails

Spinning up new environments requires reliable infrastructure setup. Your OpenAI agent uses this MCP Server to trigger `create_service` and configure the Fastly edge by querying active templates via `get_service_version`.

Setup guide

Set up Fastly MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Fastly tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Fastly tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Fastly tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Fastly Agent",
            instructions="You have access to Fastly tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent calls the `purge_all_cache` tool directly when a content update occurs. The OpenAI Agents SDK handles the asynchronous execution and returns the Fastly API response status to the agent loop. You can trace this entire execution flow in your OpenAI dashboard.

Yes, you restrict access by scoping the Fastly API token you pass to the MCP Server. When the OpenAI agent calls `list_services`, it will only see and modify the specific Fastly environments allowed by that token's permissions.

You define runtime middleware in the OpenAI Agents SDK that intercepts the `activate_service_version` tool call before it hits the Fastly network. If the agent tries to activate an untested Fastly draft, your Python code blocks the request before any traffic is affected.

Yes, you can set up a specialized routing agent in the OpenAI Agents SDK that handles general requests and hands off to a Fastly-focused agent. The specialized agent then uses Fastly tools like `get_service_stats` to report performance metrics.

Vinkius runs the server in an isolated V8 sandbox where your Fastly API tokens are injected strictly as environment variables. No configuration data or token values are stored on disk, and the ephemeral container destroys all memory states immediately after the Fastly tool call completes.

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