How to Use the Fastly MCP in AutoGen

Q: How do I register Fastly tools with an AutoGen agent?

You use the autogen-extmcp package to import the tools. Wrap your Vinkius server endpoint using the MCP adapter and pass the resulting tools list directly to your agent.

Q: How does the Fastly MCP server protect my edge traffic statistics?

Traffic stats retrieved via getservicestats are processed entirely within an isolated Vinkius sandbox. Your AutoGen agents receive the data over a secure, encrypted connection, and no telemetry is stored on our servers.

Deploy AutoGen agents that debate, verify, and execute Fastly service rollouts and cache purges with multi-agent consensus.

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 AutoGen

Create your Vinkius account to connect Fastly to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Fastly operations via AutoGen agent debate

Build a multi-agent system where one agent proposes a configuration change and another reviews it before execution. By exposing this MCP Server, your AutoGen agents cooperatively audit deployments using `get_service_version` to prevent accidental downtime. The proposal agent drafts the change, while the validator agent runs `list_version_backends` to ensure all origin servers are healthy. Only after both agree does the executor agent call `activate_service_version`.

Automate emergency rollbacks and cache purges safely

Run an incident response team of agents that monitors your edge metrics. If your performance agent detects a spike in errors, it alerts the coordinator agent to run `get_service_stats` and isolate the issue. Once the root cause is identified, the agents debate the safest recovery action. They can decide to roll back the service or call `purge_all_cache` to clear corrupted assets globally.

Manage service lifecycles with multi-agent consensus

This MCP setup prevents single-point-of-failure mistakes when cleaning up old infrastructure. Your agents run a structured check using `list_services` to identify unused or legacy configurations. A security agent verifies the service has no active traffic, while a finance agent checks the usage history. Only when both approve will the system call `delete_service` to remove the resource.

Setup guide

Set up Fastly MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Fastly tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Fastly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Fastly data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Fastly_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Fastly data")
    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 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 AutoGen

You use the `autogen-ext[mcp]` package to import the tools. Wrap your Vinkius server endpoint using the MCP adapter and pass the resulting tools list directly to your agent.

Yes, you can set up a coordinator agent that requires approval from both a QA agent and a DevOps agent. The QA agent calls `get_service_version` to verify settings before allowing `activate_service_version` to run.

Your agents coordinate to analyze error rates first. Once they agree a purge is necessary, the designated executor agent calls `purge_all_cache` to clear the edge.

You should configure a supervisor agent to intercept calls to `delete_service`. The supervisor verifies traffic levels via `get_service_stats` and blocks the deletion if the service is still active.

Traffic stats retrieved via `get_service_stats` are processed entirely within an isolated Vinkius sandbox. Your AutoGen agents receive the data over a secure, encrypted connection, and no telemetry is stored on our servers.

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