How to Use the Zingtree MCP in Vercel AI SDK

Q: How do I check Zingtree session form data with Vercel AI SDK?

You use getsessionformdata to get every piece of information entered by the user during a specific session. This raw data streams directly into your UI, allowing you to validate or display it in real time.

Q: What variables can I list for Zingtree using Vercel AI SDK?

To see all variables used within any tree, call listtreevariables. This function returns a full enumeration of available keys. Your agent client then uses this list to validate inputs before streaming the result.

Q: Can Zingtree help me structure data with Vercel AI SDK?

The gettreestructure tool provides the complete, linear organization of a specific tree. You pass this structured data to your client, which can then render it as a navigable component in your application.

Q: Where does Zingtree store session paths when using Vercel AI SDK?

The getcleansessionpath tool returns a clean, linear path identifier for any given user session. This is useful because it provides a simple string key you can use to reference the data later on.

Stream data updates to your UI using 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 Zingtree MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Session Details Live

Grab detailed information for a specific user session using `get_session_details`. This lets you show users exactly what happened during their last interaction. When you stream responses into your React or Next.js frontend, the data appears instantly. The end-user sees the results appearing in real time, not waiting on some loading spinner.

List Available Trees

Need to know what kind of decision trees exist? Call `list_trees` to pull a list of all interactive Zingtree components across the organization. Your UI can then populate itself with available options, guiding the user immediately. This tool gives you visibility into your entire product landscape. You build out the front end knowing exactly which data sources are available for the user.

Search Across All Trees

Users might need to find specific information buried deep in a workflow. Use `search_all_trees` to search text across every decision tree Zingtree manages. Your agent handles this complex query and feeds the results back instantly. This is perfect for creating powerful, interactive help documentation. You pass the data through your streamText function, letting the user see the search hits appear as they are found.

Setup guide

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

You use `get_session_form_data` to get every piece of information entered by the user during a specific session. This raw data streams directly into your UI, allowing you to validate or display it in real time.

To see all variables used within any tree, call `list_tree_variables`. This function returns a full enumeration of available keys. Your agent client then uses this list to validate inputs before streaming the result.

The `get_tree_structure` tool provides the complete, linear organization of a specific tree. You pass this structured data to your client, which can then render it as a navigable component in your application.

The `get_clean_session_path` tool returns a clean, linear path identifier for any given user session. This is useful because it provides a simple string key you can use to reference the data later on.

This MCP Server handles operational and structural data, specifically focusing on user session records, form inputs, and the internal structure of decision trees.

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