How to Use the Assembly MCP in AutoGen

Let your AutoGen agents debate and coordinate updates across Assembly workspaces and client lists.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Assembly MCP to AutoGen

Create your Vinkius account to connect Assembly 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 Assembly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven workspace audits in AutoGen

AutoGen agents work best when they can challenge each other's work via this MCP Server. By exposing `list_workspaces` and `get_workspace`, you can have an auditor agent verify workspace layouts while a manager agent suggests updates. They debate the changes before executing them. This collaborative flow ensures no workspace is misconfigured. One agent pulls the list, another checks user permissions using `list_users`, and they agree on the correct setup before presenting the final report to you.

Multi-agent debate over client and company records

Managing client relationships requires nuance. This MCP Server lets your AutoGen agents cross-reference data from `get_client` and `get_company` to resolve discrepancies. If a company name doesn't match a client record, the agents negotiate the correct fix. You can set up one agent to prioritize speed and another to focus on data accuracy. They use `list_companies` to pull the raw facts, debate the differences, and write down the verified truth.

Automated note analysis and user tracking

Let your agents handle the busywork of tracking user activity. By using `list_notes` and `get_user`, your AutoGen group chat can automatically summarize recent meeting outcomes. The agents discuss which action items belong to which user. A specialized writer agent drafts the summary, while a reviewer agent checks it against `get_note` to ensure accuracy. This multi-agent verification loop guarantees that your internal summaries are always flawless.

Setup guide

Set up Assembly 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 Assembly 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="Assembly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You import the AutoGen MCP extension and pass your Vinkius connection parameters to the streamable HTTP server utility. Then, pass the adapter-wrapped tools directly to your AssistantAgent constructor.

Yes, the tools are stateless and can be shared across your entire agent group. An analyst agent can run `list_companies` while a coordinator agent checks `list_users` in the same conversation thread.

The AutoGen MCP tool adapter handles all schema conversions automatically under the hood. It translates the server's tool definitions into the exact JSON schemas that AutoGen agents expect.

Yes, you can design a multi-agent system where one agent pulls data using `get_note` and another agent posts that information to a different platform or database.

Your workspace structures, user profiles, notes, clients, and company details remain entirely under your control. Vinkius executes all tool calls in an ephemeral, zero-trust sandbox environment, meaning no credential or raw database record is ever saved or exposed to external parties.

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