SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Zeplin MCP with Autogen

Connect Autogen to Zeplin MCP. List all project styleguides in zeplin, get all screens for a specific project, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Zeplin logoZeplin
Oauth2Api Key

Zeplin is a collaborative workspace for designers and developers to organize and hand off design projects. It streamlines design file sharing and communication for smoother product development.

24 Tools

Introduction

This guide walks you through connecting Zeplin to AutoGen using the Composio tool router. By the end, you'll have a working Zeplin agent that can browse projects and screens, review screen annotations, manage styleguide colors and text styles, and invite project members through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Zeplin account through Composio's Zeplin MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Zeplin with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Zeplin
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Zeplin tools
  • Run a live chat loop where you ask the agent to perform Zeplin operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Zeplin MCP server, and what's possible with it?

The Zeplin MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Zeplin account. It provides structured and secure access to your Zeplin workspace, so your agent can perform actions like listing projects, fetching screens, exporting assets, managing components, and collaborating with your design team on your behalf.

  • Project and styleguide management: Let your agent list, fetch, or organize your Zeplin projects and associated styleguides for faster design handoff and reference.
  • Screen and asset retrieval: Automatically pull screen details, preview images, or export assets from any project directly into your workflow, no copy-paste required.
  • Component library access: Have your agent fetch, list, or update components from your shared libraries to keep your design system in sync.
  • Commenting and collaboration: Enable your agent to read, create, or manage comments on screens or components, streamlining feedback and design review cycles.
  • Resource linking and metadata extraction: Allow your agent to extract, organize, or provide direct links to design resources and metadata, making documentation and developer handoff seamless.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Zeplin account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Zeplin via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Zeplin connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Zeplin session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["zeplin"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Zeplin tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Zeplin assistant agent with MCP tools
    agent = AssistantAgent(
        name="zeplin_assistant",
        description="An AI assistant that helps with Zeplin operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Zeplin tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Zeplin related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Zeplin tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Zeplin and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Zeplin session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["zeplin"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Zeplin assistant agent with MCP tools
        agent = AssistantAgent(
            name="zeplin_assistant",
            description="An AI assistant that helps with Zeplin operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Zeplin related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Zeplin through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Zeplin, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Zeplin action and event your agent gets out of the box.

Start OAuth authorization (PKCE)

Construct an OAuth 2.

List Project Connected Components

List connected components in a Zeplin project by project ID.

List Project Colors

List colors defined in a Zeplin project by project ID, for example to retrieve its color tokens.

Update Project Color

Tool to update a color in a Zeplin project.

Get Zeplin Project by ID

Get a Zeplin project by ID to view details about a specific project.

Invite Project Member

Invite a user to a Zeplin project by handle, with an optional role.

List Project Text Styles

List text styles in a Zeplin project by project ID to retrieve its typography tokens.

Update Project Text Style

Update an existing text style in a Zeplin project by project and text style IDs.

Delete Screen Annotation

Tool to delete a screen annotation in Zeplin.

Get Screen Annotation

Tool to fetch a single screen annotation.

List Screen Annotations

List a page of annotations for a Zeplin screen by screen ID.

Update Screen Annotation

Update a screen annotation's content, position, or type by screen and annotation IDs.

List Screen Components

List components in a Zeplin screen by screen ID.

Get Screen Section

Tool to get a single screen section.

List Screen Sections

List screen sections in a Zeplin project by project ID.

Get Screen Version

Retrieve a specific Zeplin screen version by screen and version IDs to inspect its snapshot metadata.

Create Screen Version

Tool to create a new version of a screen.

List Screen Versions

List a page of versions for a Zeplin screen to enumerate its past snapshots.

Create Styleguide Color

Create a color token in a Zeplin styleguide.

List Styleguide Colors

List color tokens in a Zeplin styleguide by styleguide ID.

Update Styleguide Color

Update a color in a Zeplin styleguide.

List Styleguide Text Styles

List a page of text styles in a Zeplin styleguide to retrieve its typography tokens.

Update Styleguide Text Style

Update typography settings of a text style in a Zeplin styleguide.

List Personal Projects

List a page of projects in the current user's personal workspace.

FRAMEWORKS

How to build Zeplin MCP Agent with another framework

Claude Code logo

Claude Code

Use Zeplin MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Zeplin MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Zeplin MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Zeplin MCP with Claude Agent SDK

Codex logo

Codex

Use Zeplin MCP with Codex

OpenClaw logo

OpenClaw

Use Zeplin MCP with OpenClaw

Hermes logo

Hermes

Use Zeplin MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Zeplin MCP with Atomic Agent

Google ADK logo

Google ADK

Use Zeplin MCP with Google ADK

LangChain logo

LangChain

Use Zeplin MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Zeplin MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Zeplin MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Zeplin MCP with LlamaIndex

CrewAI logo

CrewAI

Use Zeplin MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Zeplin MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Zeplin.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Zeplin tool your agent needs.Free to start.

Start building