How to Use the Zingtree MCP in OpenAI Agents SDK

Q: Does Zingtree support querying variable usage for specific timeframes using the MCP Server?

Yes. You can use listtreesessions to filter sessions by date range, then pair that with listtreevariables to see exactly which variables were used in those limited sessions.

Analyze complex workflows and session data using your OpenAI Agents SDK agent.

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 OpenAI Agents SDK

Create your Vinkius account to connect Zingtree 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 Zingtree with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Understand User Session Behavior with the MCP Server

Need to know what a user actually did? Your agent can get detailed records for any specific interaction via `get_session_details`. It also tracks the exact payload using `get_session_form_data`, giving you the full context of how data was entered. This is critical for debugging or compliance checks. You don't just see that a session happened; you see the precise path taken by calling `get_clean_session_path`.

Map Out Organizational Decision Trees

Figure out the architecture of your business logic using `list_trees`. Better yet, get the complete internal layout of a single workflow with `get_tree_structure`. This reveals every branch point and variable used in that specific process. If you need to audit all the variables across multiple processes, use `list_tree_variables` to pull a master list. It keeps your agent's understanding of the system robust.

Search Across All Zingtree Workflows

Don't want to manually check every tree? The `search_all_trees` tool searches text across all decision trees in your organization. This means you can quickly surface mentions of specific keywords or concepts. To narrow down the search, list sessions for a range using `list_tree_sessions`. Combine that with `search_all_trees`, and you're looking at targeted insights into user-generated content.

Setup guide

Set up Zingtree 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 Zingtree tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Zingtree 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="Zingtree Agent",
            instructions="You have access to Zingtree 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 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 OpenAI Agents SDK

The MCP Server exposes all Zingtree tools directly to your agent. Your AI client auto-discovers every available function—like `get_clean_session_path` or `list_trees`—so you just pass the server and start building.

Yes. While the agent discovers all tools, your production setup allows you to define tool sets, ensuring your specialized agents only see the functions they need—say, restricting access to just `get_session_details`.

The full trace is visible in the OpenAI dashboard. It shows which tool was called, the inputs provided to that function (like `get_session_form_data`), and the exact output—making debugging straightforward.

Yes. You can use `list_tree_sessions` to filter sessions by date range, then pair that with `list_tree_variables` to see exactly which variables were used in those limited sessions.

Absolutely. The server is built for deployment, complete with guardrails that validate every agent action before it runs. This means your system maintains data integrity when interacting with Zingtree.

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