How to Use the LiquidPlanner Classic MCP in Vercel AI SDK

Q: How do I handle authentication for LiquidPlanner Classic inside a Vercel AI SDK app?

You configure the Vinkius MCP endpoint token within your createMCPClient setup. This single token routes all requests securely, removing the need to manage raw LiquidPlanner Classic API keys on the client side.

Q: Can the Vercel AI SDK stream nested task creation in LiquidPlanner Classic?

Yes, your application can stream the execution of createtask with a specified parent ID. The end user sees the subtask appear in the UI while the background scheduler recalculates the timeline.

Q: What happens when a team member updates a task while the SDK is streaming?

The updatetask tool pushes changes directly to the workspace, forcing an immediate schedule recalculation. Your streamed UI updates to reflect the new dates returned by the server.

Feed LiquidPlanner Classic timelines directly into your Vercel AI SDK frontend without waiting for slow background syncs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiquidPlanner Classic MCP to Vercel AI SDK

Create your Vinkius account to connect LiquidPlanner Classic 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 LiquidPlanner Classic with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live project timelines with the Vercel AI SDK

`list_projects` pulls your active LiquidPlanner Classic roadmaps straight into your React or Next.js components. Users watch schedules adjust in real-time as your app streams the exact project details directly to the browser window. You don't have to deal with annoying loading spinners while waiting for API responses. Instead, this MCP Server feeds live workspace data straight into your UI components, keeping the interface snappy and responsive.

Edit tasks instantly from the edge

`update_task` modifies task details and updates dependencies right from Edge Functions. Your AI client handles the heavy lifting, changing dates or assignments based on direct user input. Because the Vercel AI SDK runs on lightweight edge runtimes, these updates happen with minimal latency. Your team gets immediate feedback on scheduling shifts without hitting cold starts or database bottlenecks.

Build nested schedules on the fly

`create_task` uses the `parent_id` parameter to place new items inside specific LiquidPlanner Classic folders or projects immediately. Your agent reads the existing structure and nests tasks where they belong. Combining this tool with `create_project` lets you generate entire project structures from a single user prompt. The Vercel AI SDK streams each step of the building process, so the user sees the hierarchy take shape.

Setup guide

Set up LiquidPlanner Classic 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 LiquidPlanner Classic 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 LiquidPlanner Classic 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 LiquidPlanner Classic. 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 LiquidPlanner Classic 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 LiquidPlanner Classic MCP in Vercel AI SDK

You configure the Vinkius MCP endpoint token within your `createMCPClient` setup. This single token routes all requests securely, removing the need to manage raw LiquidPlanner Classic API keys on the client side.

Yes, your application can stream the execution of `create_task` with a specified parent ID. The end user sees the subtask appear in the UI while the background scheduler recalculates the timeline.

This server translates complex scheduling payloads into simple tool calls like `get_project` that your LLM understands. You write less boilerplate code and let the model handle the API parameter mapping.

The `update_task` tool pushes changes directly to the workspace, forcing an immediate schedule recalculation. Your streamed UI updates to reflect the new dates returned by the server.

Your project schedules, task dependencies, and member IDs never touch external storage. Vinkius runs this MCP connector inside isolated, ephemeral execution environments that destroy themselves immediately after your session ends.

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