How to Use the FullStory MCP in Vercel AI SDK

Q: Can Vercel AI SDK stream FullStory session events to my frontend?

Yes. Your agent calls the getsessionevents tool and the SDK streams the click trails directly to the browser. Users see the DOM changes load progressively.

Q: How does the MCP Server handle data privacy for session recordings?

The deleteuser tool permanently removes privacy-sensitive telemetry and custom property links from the platform. Vinkius runs the integration inside an ephemeral V8 Isolate Sandbox. Your authentication token never touches persistent storage.

Stream FullStory session data directly into your Next.js frontend using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FullStory MCP to Vercel AI SDK

Create your Vinkius account to connect FullStory 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 FullStory with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Session Data with Vercel AI SDK

The `get_session` tool pulls page transitions and active time directly into your React components. Your AI client fetches the metadata while the user watches the UI update. You don't need a loading spinner. The data just appears on screen as the edge function resolves the request. Combine that with `get_session_events` to render click trails and DOM changes in real-time. You pass the session ID. The Vercel AI SDK streams the chronological telemetry straight to the browser. Support reps get immediate visual context without leaving your custom dashboard.

Sync Custom Tenant Data Live

The `create_update_user` tool pushes CRM attributes into the FullStory analytics boundary. Next.js server actions handle the form submission, and your agent upserts the identity instantly. Cross-device interaction boundaries update without a page refresh. When support needs background context, `get_user` retrieves the raw behavior history. The MCP Server streams total session durations and custom variables directly to your frontend. You keep support agents in your app instead of forcing them to open another tab.

Query Analytics Boundaries

The `list_segments` tool resolves saved audience definitions and 30-day population counts. Your Vue or Svelte frontend requests a specific cohort. The MCP Server executes the query and pipes the logical filter structures back to the client. Drill down further using `list_users` to expose individual session counts and behavioral profiles. You define the query criteria. The edge function streams the resulting visitor directory straight into your custom data tables.

Setup guide

Set up FullStory 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 FullStory 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 FullStory 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 FullStory. 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 FullStory 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 FullStory MCP in Vercel AI SDK

Install @ai-sdk/mcp and initialize with createMCPClient. Pass the HTTP transport URL. Call mcpClient.tools() and feed the results into streamText to start rendering session data.

Yes. Your agent calls the get_session_events tool and the SDK streams the click trails directly to the browser. Users see the DOM changes load progressively.

Always call mcpClient.close() when your edge function completes the task. This cleanly terminates the HTTP transport connection. Dropping the connection prevents memory leaks in production.

It works perfectly. The MCP protocol uses standard HTTP transports that execute fast on edge nodes. You get low-latency access to list_sessions right near your users.

The delete_user tool permanently removes privacy-sensitive telemetry and custom property links from the platform. Vinkius runs the integration inside an ephemeral V8 Isolate Sandbox. Your authentication token never touches persistent storage.

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