How to Use the LiquidPlanner Classic MCP in OpenAI Agents SDK

Q: What happens if an OpenAI Agents SDK agent tries to assign a LiquidPlanner Classic task to a non-existent member?

The agent should first run listmembers to verify the team roster. If it attempts an invalid assignment, the LiquidPlanner Classic API returns an error, which the MCP integration catches and traces on your OpenAI dashboard.

Build production OpenAI Agents SDK setups that modify LiquidPlanner Classic tasks and balance project schedules without human intervention.

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 OpenAI Agents SDK

Create your Vinkius account to connect LiquidPlanner Classic to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe scheduling with built-in agent guardrails

Production runs require guardrails to keep models from wrecking your LiquidPlanner Classic timelines. When your agent calls `update_task` or `create_project`, the OpenAI Agents SDK validates the action against your actual team capacity limits before hitting the API via this MCP Server. This setup stops your OpenAI Agents SDK agent from assigning 80 hours of work to a single resource in LiquidPlanner Classic. You get clean execution tracing on the OpenAI dashboard, showing exactly when and why a task modification happened.

Multi-agent handoffs for complex workspace updates

We split the work between specialized OpenAI Agents SDK agents to handle different parts of the LiquidPlanner Classic workspace. One agent scans workspaces using `list_workspaces` and `get_workspace`, while another handles task creation with `create_task`. The OpenAI Agents SDK manages the handoff between these specialized agents smoothly. Your scheduling agent does not need to know how to parse LiquidPlanner Classic workspace metadata; it just receives the validated workspace ID and goes to work.

Auto-discovering tools in this MCP Server

Skip the manual tool registration boilerplate entirely when connecting LiquidPlanner Classic. The OpenAI Agents SDK automatically discovers tools like `list_projects` and `get_project` the second you initialize the connection. By setting the tool list cache to true, your OpenAI Agents SDK agent system boots in milliseconds. The model immediately knows how to query LiquidPlanner Classic project states without hardcoded schemas slowing down your production runtime.

Setup guide

Set up LiquidPlanner Classic MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all LiquidPlanner Classic tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LiquidPlanner Classic tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate LiquidPlanner Classic tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="LiquidPlanner Classic Agent",
            instructions="You have access to LiquidPlanner Classic tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package, initialize the HTTP server streamable class with your Vinkius endpoint, and pass it to your OpenAI Agents SDK Agent constructor. The SDK auto-discovers all ten LiquidPlanner Classic tools instantly.

Yes. Your OpenAI Agents SDK agent can read existing schedules with `list_tasks` and then call `create_task` with the correct parent ID. The LiquidPlanner Classic engine handles the backend timeline adjustments.

You configure one OpenAI Agents SDK agent for discovery and another for editing. The first agent finds the project ID using `list_projects`, then hands off the context to the second agent to run `update_task` in LiquidPlanner Classic.

The agent should first run `list_members` to verify the team roster. If it attempts an invalid assignment, the LiquidPlanner Classic API returns an error, which the MCP integration catches and traces on your OpenAI dashboard.

Your LiquidPlanner Classic task descriptions, project names, and member lists never persist on Vinkius. Everything runs in isolated V8 sandboxes, sending data directly between your OpenAI Agents SDK runtime and the LiquidPlanner Classic API.

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