How do I find my Lanhu Access Token?

Log in to Lanhu, go to [User Settings] → [Access Token], and generate a new token. Copy it immediately as it won't be shown again.

Can I read design layer information through the agent?

Yes. Use the `list_layers` tool with the design file ID. This allows your agent to retrieve the layer structure and design nodes for that specific file.

Does Lanhu support team-based organization?

Yes. You can list all your teams using the `list_teams` tool and then explore projects and members specifically for each team using their IDs.

Lanhu MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Lanhu
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Lanhu through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Lanhu Assistant",
            instructions=(
                "You help users interact with Lanhu. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Lanhu"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Lanhu MCP Server

Empower your AI agent to orchestrate your product design workflow with Lanhu (蓝湖), the premier design collaboration platform for high-performance teams. By connecting Lanhu to your agent, you transform complex design handoffs and project coordination into a natural conversation. Your agent can instantly list your projects, retrieve design file information, audit layer structures, and even browse team comments without you needing to navigate the web interface. Whether you are managing a mobile app design or a large-scale enterprise system, your agent acts as a real-time design coordinator, keeping your assets organized and your production moving.

The OpenAI Agents SDK auto-discovers all 10 tools from Lanhu through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Lanhu, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Project Orchestration — List all accessible design projects and files across your Lanhu workspace.
Design Auditing — Retrieve detailed metadata about design files, including layers and node structures.
Collaboration Monitoring — Browse file comments and discussions to stay informed about team feedback.
Board Management — Access design boards to understand project organization and milestones.
Team Coordination — List teams and members to manage assignments and participation effectively.

The Lanhu MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Lanhu to OpenAI Agents SDK via MCP

Follow these steps to integrate the Lanhu MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Lanhu

Why Use OpenAI Agents SDK with the Lanhu MCP Server

OpenAI Agents SDK provides unique advantages when paired with Lanhu through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Lanhu + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Lanhu MCP Server delivers measurable value.

Automated workflows: build agents that query Lanhu, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Lanhu, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Lanhu tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Lanhu to resolve tickets, look up records, and update statuses without human intervention

Lanhu MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Lanhu to OpenAI Agents SDK via MCP:

get_board

Get board details

get_comments

Get file comments

get_file

Get design file info

get_project

Get project details

list_boards

List project boards

list_layers

List file layers

list_members

List team members

list_project_files

g., from Sketch, Figma, XD) within a specific project. List project design files

list_team_projects

List team projects

list_teams

List all Lanhu teams

Example Prompts for Lanhu in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Lanhu immediately.

"List all my design projects on Lanhu."

"Show me the comments for design file 'checkout-v1'."

"List the layers for file 'homepage-main'."

Troubleshooting Lanhu MCP Server with OpenAI Agents SDK

Common issues when connecting Lanhu to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Lanhu + OpenAI Agents SDK FAQ

Common questions about integrating Lanhu MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.