How to Use the Lattice MCP in OpenAI Agents SDK

Q: How does the Lattice MCP Server connect to the openai-agents-sdk?

You initialize MCPServerStreamableHttp pointing to your Vinkius endpoint and pass it to the Agent constructor. The SDK automatically discovers all nine tools like listusers during startup.

Q: Does the openai-agents-sdk cache the Lattice tool definitions?

Setting cacheToolsList=True in your Python setup keeps tool schemas in memory. This cuts down on initialization latency when your agents boot up to query listgoals.

Q: How do I handle agent handoffs when querying employee details?

Your primary router agent uses getuser to identify an employee's department. It then passes the thread to a specialized department agent to handle the rest of the workflow.

Auto-discover Lattice HR data directly inside your OpenAI Agents SDK workflow with strict guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lattice MCP to OpenAI Agents SDK

Create your Vinkius account to connect Lattice 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 Lattice with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync HR contexts with OpenAI Agents SDK

The `list_users` tool pulls your actual Lattice employee directory directly into your OpenAI Agents SDK runtime. This integration lets your agent map Slack IDs to corporate email profiles without maintaining static, out-of-sync databases. Your agent then routes onboarding tasks using the built-in handoff mechanics. For instance, the system checks `list_tasks` to verify completion before transferring the session to an HR routing specialist.

Audit performance metrics via MCP Server

The `list_reviews` tool exposes active performance cycles to your analytical OpenAI Agents SDK pipelines. Your agents inspect these cycle timelines to flag which departments have pending submissions. By passing these metrics to the OpenAI tracing dashboard, you verify every decision step the agent takes. This ensures full transparency when evaluating historical performance data.

Track organizational milestones dynamically

The `list_goals` tool reveals corporate OKRs directly to your autonomous OpenAI agents. This allows the model to evaluate if team outputs align with high-level corporate targets. Your agent calls `get_goal` to inspect specific metric blockers. It then flags stalled initiatives to managers before small delays turn into major project bottlenecks.

Setup guide

Set up Lattice 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 Lattice tools at runtime.
3

Create your Agent

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

Run the agent

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

You initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint and pass it to the Agent constructor. The SDK automatically discovers all nine tools like `list_users` during startup.

Yes, you configure this at the Vinkius gateway level or by filtering the tool list before passing it to the agent. This prevents your agent from accessing sensitive tools like `get_review` if it only needs to check tasks.

Setting `cacheToolsList=True` in your Python setup keeps tool schemas in memory. This cuts down on initialization latency when your agents boot up to query `list_goals`.

Your primary router agent uses `get_user` to identify an employee's department. It then passes the thread to a specialized department agent to handle the rest of the workflow.

Vinkius processes your employee reviews, goals, and feedback in isolated V8 sandboxes. Your API credentials never leak to the client code, keeping private HR metrics locked down.

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