How to Use the Fastly MCP in Vercel AI SDK

Q: How do I check Fastly status in Vercel AI SDK?

Connect the server via the HTTP transport and call the getservice tool. You'll get immediate feedback on your service status inside your React component.

Q: Can Vercel AI SDK trigger a Fastly purge?

Yes, just map purgeallcache to a function in your agent. The agent executes the purge request as soon as your trigger condition is met.

Stream Fastly CDN metrics and service states directly into your Vercel AI SDK interface for real-time edge management.

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 Vercel AI SDK

Create your Vinkius account to connect Fastly to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live edge monitoring in Vercel AI SDK

Feed your UI live performance data by piping the `get_service_stats` tool into your stream. Your users see cache hit rates and request latency as they happen. Stop guessing about edge performance. Use `list_services` to populate your dashboard dropdowns and let your agents handle the heavy lifting while the user watches the data flow.

Instant CDN control for Vercel AI SDK

Trigger cache invalidations without leaving your app code. A simple `purge_all_cache` call clears the edge instantly when your backend logic detects a data update. Keep your content fresh by automating the activation of new configurations. Use `activate_service_version` to push changes the second your deployment script finishes its build.

Backend inspection with Vercel AI SDK

Verify your origin health before pushing code changes. Use `list_version_backends` to check if your endpoints are responding correctly. This MCP Server provides the exact state of your infrastructure so your frontend agent knows exactly what it's touching. Get the full picture with `get_service_version` before you commit to a change.

Setup guide

Set up Fastly MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Fastly tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Fastly transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Connect the server via the HTTP transport and call the `get_service` tool. You'll get immediate feedback on your service status inside your React component.

Yes, just map `purge_all_cache` to a function in your agent. The agent executes the purge request as soon as your trigger condition is met.

Vinkius handles the auth token securely. Your agent only accesses the specific service IDs you provide, keeping your configuration isolated.

The server uses paginated tool responses. You'll get the data in chunks, preventing memory spikes in your edge functions.

Wrap your tool calls in a standard logger. You'll see exactly which `activate_service_version` call triggered a change in your deployment logs.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.