How to Use the Ellie Planner MCP in LangChain

Q: How do I connect my Ellie Planner account to a LangChain agent?

You use the MultiServerMCPClient and pass your Vinkius endpoint URL. Then, call client.gettools() and pass the resulting list to your agent's constructor. LangChain handles the rest.

Q: What's the best way to get all overdue tasks from Ellie Planner in LangChain?

Create a chain that first calls listtasks. Then, add a custom function link in the chain that parses the dates and filters for overdue items. This keeps your agent's logic clean and separated.

Q: Is it possible to build a project reporting agent with Ellie Planner and LangChain?

Absolutely. Your agent can listtasks for a specific project, count how many are completed versus active, and format a summary. This is a classic use case for chaining tool calls with data processing.

Build agents that plan and execute projects in Ellie Planner using LangChain's composable chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ellie Planner MCP to LangChain

Create your Vinkius account to connect Ellie Planner 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 Ellie Planner with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Together Project Plans

Give your agent a goal, not just a command. It can `list_lists` to find the right project, `create_task` to add a new objective, then `get_task` to confirm the details before moving on. Each step informs the next. This isn't a simple script. It's a reasoning pipeline. Your agent decides the sequence of operations based on the results it gets back from Ellie Planner, letting it adapt to new information on the fly.

Automate Repetitive Task Workflows

Build chains that handle the grunt work. Create a workflow that runs `list_tasks` every morning, identifies items with past-due dates, and automatically calls `update_task` to flag them for review. You define the logic once, and your LangChain agent executes it perfectly every time. This is how you connect your planning tool directly to an execution engine, no manual steps required.

Your Project Data, Your LangChain Agent

The `get_tools()` function gives your agent a ready-to-use toolkit for Ellie Planner. It’s not just calling an API; it’s giving your agent the ability to reason with your project data. The MCP protocol handles the schema translation automatically. Every tool call, input, and output can be traced in LangSmith. You get full visibility into your agent's decisions, making it easy to debug and refine your project management bots.

Setup guide

Set up Ellie Planner 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 Ellie Planner 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({
    "ellie-planner-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 Ellie Planner 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 Ellie Planner. 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 Ellie Planner 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 Ellie Planner MCP in LangChain

You use the `MultiServerMCPClient` and pass your Vinkius endpoint URL. Then, call `client.get_tools()` and pass the resulting list to your agent's constructor. LangChain handles the rest.

Yes. You can build a chain that loops through a list of objectives and calls `create_task` for each one. The agent can even decide which list to add them to by calling `list_lists` first.

Create a chain that first calls `list_tasks`. Then, add a custom function link in the chain that parses the dates and filters for overdue items. This keeps your agent's logic clean and separated.

Absolutely. Your agent can `list_tasks` for a specific project, count how many are completed versus active, and format a summary. This is a classic use case for chaining tool calls with data processing.

LangChain agents process your Ellie Planner task data—titles, labels, due dates—to make decisions. If you use LangSmith, these tool inputs and outputs are traced. Review your LangSmith data retention policies to control how that information is stored.

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