How to Use the Easelly MCP in AutoGen

Q: How do I register Easelly MCP tools with an AutoGen AssistantAgent?

Install autogen-extmcp and use mcpservertools to fetch the tools from your Vinkius endpoint. Pass the resulting tool list directly into your AssistantAgent constructor.

Q: How does schema conversion work in this setup?

The McpToolAdapter handles all schema conversions automatically under the hood. Your AutoGen agents can call the tools using standard JSON payloads without manual schema mapping.

Let your AutoGen agents debate and collaborate using this MCP server to design, review, and export Easelly infographics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Easelly MCP to AutoGen

Create your Vinkius account to connect Easelly to AutoGen 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 Easelly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent design reviews with AutoGen

The `update_infographic` tool lets your AutoGen design agent apply layout changes that have been debated and approved by your copywriter and editor agents. Instead of a single model making unchecked edits, one AutoGen agent proposes layout updates to the Easelly template while another reviews them for consistency. This collaborative AutoGen workflow ensures your final Easelly visual reports meet brand guidelines before any files are generated. The AutoGen agents negotiate layout placements, verify text length, and only commit changes once they reach a consensus.

Automate file generation via an MCP Server

The `generate_pdf` tool allows your AutoGen publishing agent to export the finished Easelly infographic once the review agents approve the layout. This separation of concerns means your rendering tools are only called after the design has been thoroughly vetted by the AutoGen group. If the AutoGen layout review agent flags an overlapping text block, the system halts the export and sends the design back to the editing agent. You save processing time by only rendering high-resolution Easelly documents that are guaranteed to look correct.

Build visual assets from scratch using agent consensus

The `create_infographic` tool initiates a new Easelly canvas based on the structural decisions made during your multi-agent AutoGen conversation. Your AutoGen planning agent outlines the sections, while the design agent builds the initial layout blocks. By letting AutoGen agents debate the structure before creation, you avoid chaotic, unorganized visual layouts in Easelly. The resulting design is clean, structured, and perfectly aligned with the data points discussed during the AutoGen agent session.

Setup guide

Set up Easelly MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Easelly tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Easelly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Easelly data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

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

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Easelly_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Easelly data")
    print(result.messages[-1].content)

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 Easelly. 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 Easelly 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 Easelly MCP in AutoGen

You assign different roles to your agents, such as a designer agent that calls `update_infographic` and a reviewer agent that inspects the layout JSON. They debate changes in a group chat before committing them.

Yes, you can connect your local AutoGen setup to the hosted Vinkius endpoint using the `StreamableHttpServerParams` transport. This gives your agents access to the tools without local installation headaches.

Install `autogen-ext[mcp]` and use `mcp_server_tools` to fetch the tools from your Vinkius endpoint. Pass the resulting tool list directly into your `AssistantAgent` constructor.

The `McpToolAdapter` handles all schema conversions automatically under the hood. Your AutoGen agents can call the tools using standard JSON payloads without manual schema mapping.

All generated PNG and PDF files are processed inside secure, ephemeral V8 sandboxes. Your visual assets are never stored permanently, ensuring strict data boundaries for your corporate reports.

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