How to Use the Howspace MCP in AutoGen

Q: Can I create an AutoGen agent to monitor my Howspace campaigns?

Absolutely. You can create a MonitorAgent whose only job is to periodically call listcampaigns and listworkspaces, reporting any changes or anomalies to you or another agent for action.

Assemble teams of AutoGen agents to debate, plan, and execute your development strategy in Howspace.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Howspace MCP to AutoGen

Create your Vinkius account to connect Howspace 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 Howspace with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Plan Initiatives with Agent Debates

AutoGen lets you model real-world team dynamics with code. An "L&D Planner" agent can propose a new series of workshops by suggesting a call to the `create_workspace` tool. Then, a "Finance" agent can challenge that plan. It can use `list_workspaces` to check how many are already active and argue against sprawl. The agents debate until they reach a consensus that you, the manager, approve. It's planning, but with agents.

Delegate Howspace Admin Tasks

Give your agent team a goal, not a script. Tell them: "Enroll the new marketing hires into their Q3 training." One agent finds the people, another finds the right workspace with `get_workspace`, and a third executes the `add_participant` call. This isn't a simple workflow; it's a conversation managed by the AutoGen framework. The agents handle exceptions, ask for clarification, and report back on their progress. You're managing a team of specialists that use the tools from this MCP server.

Simulate and Audit Scenarios

Before you roll out a major training campaign, have your agents model it. One agent can use `list_campaigns` to outline the plan, while another plays the role of a new user and tries to confirm its own access with `get_me`. You can also build an auditor agent team. They periodically run `list_workspaces` and `list_participants` to check for empty workshops or inactive users, flagging them for cleanup. The agents work together to keep your Howspace instance tidy.

Setup guide

Set up Howspace 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 Howspace 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="Howspace_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

AutoGen provides a conversational framework. One agent can propose an action, like calling `create_workspace`, and other agents can review, critique, or approve it before the tool is actually executed on your Howspace instance.

Absolutely. You can create a `MonitorAgent` whose only job is to periodically call `list_campaigns` and `list_workspaces`, reporting any changes or anomalies to you or another agent for action.

You'd set up a two-agent conversation. The first agent calls `add_participant`. The second agent then follows up by calling `list_participants` on the same workspace to confirm the user was added correctly.

Yes. You connect using a Vinkius endpoint URL and a single token. All communication between your AutoGen agents and the Howspace tools is routed through Vinkius's secure, ephemeral infrastructure.

Your agents can access any data the tools they're permitted to use can return. For instance, an agent using `list_participants` will see user names and emails from Howspace. All data access happens within the secure V8 isolate sandbox provided by the MCP Server.

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