How to Use the Moxie MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle creating a client and project in Moxie?

Your agent calls the createclient tool first. Once it gets a client ID back, it passes that ID to the createproject tool. The SDK's handoff features let you build multi-step workflows like this easily.

Q: What's the best way to find a specific project in Moxie with the OpenAI Agents SDK?

Use the searchprojects tool with a client name or project status as a parameter. Your agent can parse the results and find the exact project ID needed for other actions, like logging time or creating an invoice.

Q: Can I build an agent that automatically invoices clients at the end of the month?

Absolutely. You can create a scheduled agent that runs searchprojects for active work, then uses createinvoice for any clients with unbilled time entries. The tracing in the OpenAI dashboard shows you exactly what it did.

Build production-grade agency bots with Moxie and the OpenAI Agents SDK. Manage clients, projects, and invoices with built-in safety checks.

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 OpenAI Agents SDK

Create your Vinkius account to connect Moxie to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Your Client Onboarding

This toolset connects your agent directly to Moxie's core client and project functions. Your agent can `create_client` for new business leads, then immediately `create_project` to get work started. It's all tied together. No more manual data entry between systems. When a client is approved, the agent just runs the sequence. You can even have it `search_contacts` to avoid duplicates before creating a new client record.

Financial Operations for OpenAI Agents SDK

Give your agent control over the money flow. It can use `create_time_entry` and `create_expense` to log billable work and costs against specific projects. This isn't just data logging; it's building the foundation for accurate billing. When it's time to get paid, the agent uses `create_invoice`, pulling all unbilled time and expenses for a client. You can even build a process for it to `search_invoices` to check payment status before sending reminders. The OpenAI Agents SDK guardrails ensure it won't accidentally send a duplicate invoice.

Manage Tasks and Tickets

Connect your internal operations to your agent. Use the `create_task` tool to assign work to your team right from a chat session. Your agent can parse a client request and turn it into actionable items in Moxie. It also handles client issues. When a problem comes in, the agent can `create_ticket` in Moxie's support system, linking it to the right client and project. This keeps all communication and work organized in one place, powered by this MCP connection.

Setup guide

Set up Moxie MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Moxie tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Moxie tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Moxie tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Moxie Agent",
            instructions="You have access to Moxie tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent calls the `create_client` tool first. Once it gets a client ID back, it passes that ID to the `create_project` tool. The SDK's handoff features let you build multi-step workflows like this easily.

Yes. While this MCP server exposes all 12 Moxie tools, you configure which ones your agent can access in its definition. This is a standard safety practice for production agents.

Use the `search_projects` tool with a client name or project status as a parameter. Your agent can parse the results and find the exact project ID needed for other actions, like logging time or creating an invoice.

Absolutely. You can create a scheduled agent that runs `search_projects` for active work, then uses `create_invoice` for any clients with unbilled time entries. The tracing in the OpenAI dashboard shows you exactly what it did.

This server processes client names, contact details, project data, tasks, and financial records like invoices and expenses. Your Vinkius endpoint is sandboxed, and all authentication is handled by a single token, keeping your Moxie credentials isolated.

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