How to Use the Planhat MCP in OpenAI Agents SDK

Q: How do I use the Planhat MCP server with the OpenAI Agents SDK?

First, pip install openai-agents. Then, you create an MCPServerStreamableHttp instance with your Vinkius URL and pass it to your Agent's constructor. The tools are discovered automatically, so there's no manual mapping.

Q: Can I see all my Planhat companies from my OpenAI agent?

Yes. Your agent uses the listplanhatcompanies tool to get the full list. You can then have it analyze the results or pass the data to another specialized agent to identify at-risk accounts.

Q: What's the best way to track renewals in Planhat using the OpenAI Agents SDK?

Have your agent use listplanhatassets and listplanhatlicenses to build a renewal report. Because the OpenAI SDK gives you full tracing, you can review a complete log of how the agent gathered the data and reached its conclusions.

Manage customer success in Planhat with an OpenAI Agents SDK agent that has built-in guardrails. Get account data without risking unexpected actions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Planhat MCP to OpenAI Agents SDK

Create your Vinkius account to connect Planhat to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Planhat with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Check Account Health, Safely

Your agent can pull a complete customer picture using `get_planhat_company` and `list_planhat_notes`. You get the context you need for a QBR or an escalation, right in your agent's workflow. Here’s the key: the OpenAI Agents SDK gives you tracing and guardrails. You can see exactly why your agent decided to pull certain data, and it won't perform unapproved operations. It’s a safe way to let an agent access your customer information.

Track Users and Licenses

Get a clear view of adoption and renewal status. Your agent can call `list_planhat_end_users` to spot drops in active users or use `list_planhat_licenses` to flag upcoming expiration dates. This is perfect for building specialized agent teams. One agent can monitor user activity while another focuses on the renewal pipeline, handing off accounts that need attention. It automates the digging so your CSMs can do the talking.

Run CS Ops with your OpenAI Agent

Offload the administrative work of customer success. Let your agent use `list_planhat_projects` and `list_planhat_tasks` to assemble a status report on all open initiatives for a key account. Connect this to other tools. For instance, after summarizing a meeting from `list_planhat_conversations`, the agent can then check for related open tasks in Planhat. This Planhat MCP Server connects your agent to the ground-truth data it needs to be useful.

Setup guide

Set up Planhat 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 Planhat tools at runtime.
3

Create your Agent

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

Run the agent

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

First, `pip install openai-agents`. Then, you create an `MCPServerStreamableHttp` instance with your Vinkius URL and pass it to your Agent's constructor. The tools are discovered automatically, so there's no manual mapping.

Yes. Your agent uses the `list_planhat_companies` tool to get the full list. You can then have it analyze the results or pass the data to another specialized agent to identify at-risk accounts.

Have your agent use `list_planhat_assets` and `list_planhat_licenses` to build a renewal report. Because the OpenAI SDK gives you full tracing, you can review a complete log of how the agent gathered the data and reached its conclusions.

This server provides read-only tools for Planhat. It’s built for agents that need to gather context—like pulling conversation history with `list_planhat_conversations`—before a human takes action.

This server only reads Planhat data like company details and conversation logs. Your Vinkius endpoint token is the only credential involved. All operations run in an ephemeral, zero-trust sandbox that is destroyed the moment your agent's request is complete.

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