How to Use the Planhat MCP in AutoGen

Q: Can AutoGen agents collaborate on Planhat customer notes?

Yes, an agent can retrieve historical updates using listplanhatnotes and share that context with other agents in the group chat. This allows your entire AutoGen team to stay aligned on recent account milestones.

Build multi-agent AutoGen teams that debate customer health and coordinate Planhat tasks autonomously using MCP.

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 AutoGen

Create your Vinkius account to connect Planhat to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Let AutoGen agents debate customer health metrics

`get_planhat_company` provides the raw company data that your AutoGen agents use to debate and assess account health. A dedicated success agent can analyze the company details while a finance agent checks contract terms, converging on a shared plan. This debate prevents knee-jerk automated decisions. By passing the output of `list_planhat_licenses` to multiple agents, your system verifies that active seat usage matches the customer's contract before flagging them for churn.

Coordinate Planhat tasks via AutoGen multi-agent consensus

`list_planhat_tasks` allows your AutoGen agent team to view, discuss, and prioritize customer follow-ups without manual intervention. One agent can review outstanding tasks while another matches them against customer notes to suggest the next logical step. The tools are registered directly with your AssistantAgent using the AutoGen MCP adapter. This means your agents can execute task lookups and assign follow-ups autonomously once they reach a consensus on the best course of action.

Audit customer onboarding projects with specialized agents

`list_planhat_projects` pulls live onboarding milestones, enabling your AutoGen agents to audit project delivery timelines. A project manager agent can flag delayed milestones while a customer success agent drafts a remedial action plan. This multi-perspective review ensures no detail is missed. The agents cross-reference the project status with notes retrieved via `list_planhat_notes` to verify if external delays were already communicated to the team.

Setup guide

Set up Planhat MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Planhat tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Planhat_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Planhat data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Planhat_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Planhat data")
    print(result.messages[-1].content)

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 AutoGen

AutoGen agents use conversational consensus to resolve conflicts before executing tools. For example, if one agent wants to mark a task as complete, it must first justify the decision to the reviewer agent using data pulled from `list_planhat_tasks`.

Yes, you can filter the tool list returned by the MCP Server before passing it to your AutoGen AssistantAgent. This lets you restrict sensitive tools like `list_planhat_licenses` to specific financial agents.

The McpToolAdapter automatically translates the JSON schema of `get_planhat_company` into the format required by your AutoGen agents. You do not need to manually map parameters or write custom translation layers.

Yes, an agent can retrieve historical updates using `list_planhat_notes` and share that context with other agents in the group chat. This allows your entire AutoGen team to stay aligned on recent account milestones.

Your Planhat company records, task lists, and project notes are processed entirely in memory within a zero-trust V8 MCP sandbox. No data is stored on Vinkius, and the endpoint token is discarded immediately after the session closes.

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