How to Use the Lanhu MCP in CrewAI

Q: How do CrewAI agents share Lanhu design context?

CrewAI agents pass the outputs of Lanhu tools like getproject through their shared memory. For example, the planning agent finds the project details, and the developer agent uses that ID to fetch assets. This maintains a single source of truth across the entire execution run.

Q: Can I run a Lanhu design audit using CrewAI agents?

Yes, you can deploy a crew where one agent runs listboards to find updates and another runs listlayers to check naming conventions. This automates your entire Lanhu audit pipeline.

Q: How do we handle Lanhu designer feedback updates autonomously in CrewAI?

Set up a loop where a monitoring CrewAI agent polls getcomments at set intervals. If new feedback is detected in Lanhu, the agent escalates the issue to a developer agent to update the codebase.

Deploy a crew of specialized design-to-code agents using CrewAI and the Lanhu 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 Lanhu MCP to CrewAI

Create your Vinkius account to connect Lanhu to CrewAI 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 Lanhu with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Lanhu design audits with this MCP Server

`list_team_projects` allows your CrewAI manager agent to map out active Lanhu design workspaces and assign tasks to specialist agents. This MCP Server gives your entire crew access to the design hierarchy. A CrewAI researcher agent uses `list_boards` to find the target Lanhu artboards, while an analyst agent inspects the layers. They work in parallel to prepare design reports without human intervention.

Translate Lanhu layers into React code using CrewAI

`list_layers` provides the raw Lanhu node data that your CrewAI developer agent needs to write UI code. The agent parses the layout tree, identifying buttons, inputs, and text blocks. Meanwhile, a CrewAI quality assurance agent calls `get_comments` to verify if there are any outstanding Lanhu feedback items that need to be addressed before writing the code. By verifying these details first, the crew avoids building outdated components.

Extract and optimize Lanhu assets using CrewAI

`list_project_files` allows your CrewAI asset agent to track down all exported PNGs and SVGs in a Lanhu project. It identifies which files need optimization before they go into production. The CrewAI agent then runs `get_file` to pull down the Lanhu asset data and passes it to an optimization tool. By automating compression, you keep your repository lightweight and high-resolution assets optimized.

Setup guide

Set up Lanhu MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Lanhu tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Lanhu Analyst",
    goal="Access and analyze Lanhu data via MCP.",
    backstory="Expert analyst with direct Lanhu access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Lanhu transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Lanhu Analyst",
        goal="Access and analyze Lanhu data via MCP.",
        backstory="Expert analyst with direct Lanhu access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Lanhu transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 Lanhu. 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 Lanhu 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 Lanhu MCP in CrewAI

CrewAI agents pass the outputs of Lanhu tools like `get_project` through their shared memory. For example, the planning agent finds the project details, and the developer agent uses that ID to fetch assets. This maintains a single source of truth across the entire execution run.

Pass the Lanhu MCP Server URL directly in your CrewAI Agent's `mcps` configuration array. For advanced setups, use `MCPServerHTTP` to filter which tools are exposed to specific agents.

Yes, you can deploy a crew where one agent runs `list_boards` to find updates and another runs `list_layers` to check naming conventions. This automates your entire Lanhu audit pipeline.

Set up a loop where a monitoring CrewAI agent polls `get_comments` at set intervals. If new feedback is detected in Lanhu, the agent escalates the issue to a developer agent to update the codebase.

This MCP Server protects your team data by running all team member lists, project IDs, and asset details within ephemeral V8 isolates. No Lanhu design files or team credentials are saved to persistent storage during CrewAI execution.

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