How to Use the Easelly MCP in LangChain

Q: How do I pass Easelly tool outputs to other LangChain components?

Use the MultiServerMCPClient to fetch the tools, then feed them into your agent executor. The output of tools like generatejson flows directly into your next chain link as a standard string payload.

Q: Can I track Easelly API latency inside LangChain?

Yes, every call to updateinfographic or generatepdf shows up in LangSmith automatically. You can monitor the exact execution time, payload size, and token usage for each design step.

Q: What is the setup process for this integration?

Install langchain-mcp-adapters and langgraph via pip. Initialize the client, call gettools(), and pass those tools directly to your agent constructor to start building visual MCP workflows.

Generate visual reports directly inside your LangChain pipelines using this MCP server to feed live chain outputs straight into Easelly.

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 LangChain

Create your Vinkius account to connect Easelly to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build visual data pipelines with LangChain agents

The `create_infographic` tool lets your LangChain agent generate a fresh visual canvas whenever a data chain finishes running. Your agent can instantly kick off a multi-step LangChain pipeline, taking raw numbers from a database query and turning them into an Easelly layout without manual copy-pasting. Since LangChain handles state transitions across chain links, the agent takes the newly minted Easelly ID and immediately feeds it into subsequent design steps. You watch the entire execution path inside LangSmith, tracking exactly how your data transforms from raw SQL rows into a polished Easelly visual asset.

Chain automated visual updates in real time

The `update_infographic` tool modifies your existing Easelly templates by injecting fresh metrics directly into the layout elements. Your LangChain agent reads the current layout structure, maps your new data points to the correct coordinates, and writes the changes in a single pass. This means you can build autonomous LangChain cron jobs that fetch weekly performance metrics, verify the numbers, and update your Easelly dashboards. Every single tool call is recorded as a LangSmith trace, letting you debug layout shifts or data mismatches before exporting the final file.

Export polished PDFs straight from your MCP Server

The `generate_pdf` tool converts your updated Easelly design canvas into a print-ready document format instantly. LangChain coordinates this by passing the final template ID to the render engine, giving you a static file path your agent can send to Slack or email. Combining this Easelly rendering tool with other API integrations in your LangChain graph lets you build full end-to-end reporting agents. You get a reliable, repeatable LangChain pipeline that outputs high-resolution documents without ever opening a web browser or dragging a single element.

Setup guide

Set up Easelly MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Easelly tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "easelly-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Easelly transactions"
    })
    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 LangChain

Use the `MultiServerMCPClient` to fetch the tools, then feed them into your agent executor. The output of tools like `generate_json` flows directly into your next chain link as a standard string payload.

Yes, every call to `update_infographic` or `generate_pdf` shows up in LangSmith automatically. You can monitor the exact execution time, payload size, and token usage for each design step.

Vinkius manages the authentication layer, exposing a single endpoint token for your client. Your LangChain initialization code only needs to point to this secure HTTP transport URL.

Install `langchain-mcp-adapters` and `langgraph` via pip. Initialize the client, call `get_tools()`, and pass those tools directly to your agent constructor to start building visual MCP workflows.

Your layout configurations and design templates are processed inside secure, ephemeral V8 isolates. No raw layout JSON or export data is stored on Vinkius servers after the rendering process completes.

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