How to Use the AssessTEAM MCP in AutoGen

Q: How can I set up multiple AutoGen agents to use AssessTEAM tools?

You use the mcpservertools function to load the tools from this MCP server. Then, you pass that list of tools to each AssistantAgent in your group, allowing them to call functions like listemployees.

Use AutoGen to build agent teams that debate and manage your AssessTEAM project and performance data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AssessTEAM MCP to AutoGen

Create your Vinkius account to connect AssessTEAM to AutoGen 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 AssessTEAM with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Project Analysis

Give a team of AutoGen agents access to the AssessTEAM tools. One agent, the "Analyst," can use `get_profitability_report` and `list_timesheets` to gather raw data on a project. It then passes its findings to a "Strategist" agent. The Strategist agent can challenge the Analyst's conclusions or propose resource shifts. They debate the options before presenting a single, consensus-driven recommendation. It's decision-making with built-in checks and balances.

Debate-Driven Performance Planning

An HR-focused agent group can prepare for performance reviews. One agent uses `list_performance_evaluations` to pull an employee's history. A second agent cross-references that with project contributions using `list_projects` and `list_timesheets`. This isn't just data fetching; it's a conversation enabled by the MCP tools. The agents can discuss discrepancies, weigh positive feedback against project outcomes, and draft a balanced summary for a human manager to use.

An AutoGen Group for Team Management

This MCP server gives your agents the tools to discuss team structure. A "Manager" agent can call `list_organizational_teams` and `list_employees` to see the current roster. It can then task a "Planner" agent with a goal. The Planner might use `list_timesheets` to identify overworked engineers and propose moving someone. The Manager agent can then critique that proposal, simulating a real management meeting.

Setup guide

Set up AssessTEAM 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 AssessTEAM 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="AssessTEAM_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent AssessTEAM 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="AssessTEAM_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent AssessTEAM 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 AssessTEAM. 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 AssessTEAM 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 AssessTEAM MCP in AutoGen

You use the `mcp_server_tools` function to load the tools from this MCP server. Then, you pass that list of tools to each AssistantAgent in your group, allowing them to call functions like `list_employees`.

Yes, that's the core AutoGen pattern. An "executor" agent calls `list_projects` and posts the raw JSON data in the chat. A separate "critic" agent can then read that data and comment on it.

A great use case is risk analysis on this MCP server. Have one agent pull a project's `get_profitability_report` from AssessTEAM, and another agent argue for or against continuing the project based on that data.

The agents decide based on the conversation history and the user's prompt. If you ask them to "review project financials," the agent with the AssessTEAM tools will likely choose `get_profitability_report`.

Yes. All tool calls from this MCP server, including those fetching performance evaluations and employee lists, run inside a Vinkius V8 Isolate Sandbox. The data is ephemeral and only exists for the duration of the agent conversation.

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