How to Use the Moxie MCP in AutoGen

Q: How do AutoGen agents access Moxie tools?

You use the mcpservertools function with the Moxie server URL to register all 12 tools. AutoGen automatically maps these to your AssistantAgent instances, allowing them to debate when to run createtask or createinvoice.

Q: Can AutoGen agents collaborate on a single Moxie project?

Yes, one agent can search for existing work using searchprojects while another logs hours with createtimeentry. They share context in their group chat to coordinate actions.

Build multi-agent AutoGen debates to manage your Moxie projects and invoices using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moxie MCP to AutoGen

Create your Vinkius account to connect Moxie 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 Moxie with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run consensus-driven billing audits in AutoGen

The `search_invoices` tool gives your AutoGen billing agents the raw financial data they need to audit client accounts. While one agent flags late payments, a second agent cross-references active projects using `search_projects` to see if work is still active. Once they agree on the outstanding balance, a third agent executes `create_invoice` to bill the client. This multi-agent debate ensures you never send incorrect bills or double-charge a customer.

Resolve support tickets via agent negotiation

The `create_ticket` tool allows AutoGen to log client issues and begin an automated resolution debate. A customer-facing agent drafts the ticket details, while a technical agent looks up workspace users via `list_users` to find the right owner. If a developer is overbooked, the agents negotiate task priority and use `create_task` to reschedule lower-priority work. You get an automated project coordinator that balances team capacity dynamically.

Automate agency operations using AutoGen MCP tools

The `create_client` tool lets your onboarding agents spin up a new client portal the second a lead closes. A finance agent logs initial setup fees with `create_expense`, while a project agent sets up the workspace using `create_project`. This MCP Server integration allows multiple specialized agents to collaborate on a single client onboarding event. They verify each other's work before logging the final onboarding hours via `create_time_entry`.

Setup guide

Set up Moxie 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 Moxie 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="Moxie_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You use the mcp_server_tools function with the Moxie server URL to register all 12 tools. AutoGen automatically maps these to your AssistantAgent instances, allowing them to debate when to run `create_task` or `create_invoice`.

Yes, one agent can search for existing work using `search_projects` while another logs hours with `create_time_entry`. They share context in their group chat to coordinate actions.

You provide a single Vinkius endpoint token to the MCP Server configuration. AutoGen agents execute actions securely through Vinkius without ever seeing your raw Moxie API keys.

The server supports both stdio and Streamable HTTP transports. This lets you run your multi-agent conversations locally or host them in a cloud environment.

Your logged hours and timesheets are shielded by the Vinkius V8 Isolate sandbox. This architecture guarantees that your operational data is processed in a secure, ephemeral environment and never leaked.

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