How to Use the Sally MCP in OpenAI Agents SDK

Q: How does Sally integrate with the OpenAI Agents SDK?

You instantiate the server via MCPServerStreamableHttp and pass it to your agent constructor. The SDK discovers all 12 tools automatically, allowing immediate execution of tasks.

Connect your OpenAI Agents SDK to Sally. Manage frontline tasks and timesheets with built-in guardrails for production environments.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sally MCP to OpenAI Agents SDK

Create your Vinkius account to connect Sally to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sally with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automated task management for OpenAI Agents SDK

Your agent handles project assignments without manual input. Use `create_task` to assign work or `update_task` to reflect shift changes in real-time. This MCP Server provides the structure your agent needs to maintain data integrity. It maps every action directly to your workspace, keeping deskless teams aligned.

Real-time communication via Sally MCP Server

Agents push updates to frontline staff using `add_comment`. This ensures everyone stays informed on high-priority items without needing a dedicated desktop station. Your agent can pull the full context using `get_board` before sending messages. It keeps the feedback loop tight and accurate.

Reporting and tracking for your agent

Generate accurate labor data using `get_timesheet_report`. Your agent can trigger these reports to keep operations managers updated on project progress. Use `list_projects` to scan your entire workspace. The agent then digs into specific details with `get_project` to provide status snapshots.

Setup guide

Set up Sally 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 Sally tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Sally 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="Sally Agent",
            instructions="You have access to Sally 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 Sally. 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 Sally 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 Sally MCP in OpenAI Agents SDK

You instantiate the server via `MCPServerStreamableHttp` and pass it to your agent constructor. The SDK discovers all 12 tools automatically, allowing immediate execution of tasks.

Yes. The server provides structured outputs that fit your agent's requirements. You can use the built-in tracing to ensure every action is logged and verified.

Absolutely. Vinkius handles the auth and endpoint security, so your agent only accesses what you authorize. Your data stays isolated within your specific session.

It does. The server is designed for async context managers, matching the non-blocking nature of your agent architecture. You get high-performance tool execution without stalling your main loop.

The server accesses your project boards, task lists, and timesheet reports. It only reads and writes the specific records you explicitly trigger through your agent.

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