How to Use the Ellie Planner MCP in LlamaIndex

Q: How do I use Ellie Planner with a LlamaIndex RAG setup?

First, use the McpToolSpec to load the Ellie Planner tools. Then, use a data loader to run listtasks and ingest the results into your vector index. Your agent can now query this index to answer questions.

Q: Can LlamaIndex search through all my tasks in Ellie Planner?

Yes. You configure it to fetch tasks using listtasks and gettask, then it builds a local or remote vector index. All subsequent searches from your agent use this index for fast, semantic retrieval.

Q: Is it possible to update tasks in Ellie Planner from LlamaIndex?

It is. Once the McpToolSpec provides the tools to your agent, it can call updatetask just like any other function. For example, an agent could find overdue tasks and automatically add a 'Follow-up' label.

Turn your Ellie Planner projects into a searchable knowledge base with LlamaIndex and answer questions with your data.

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 LlamaIndex

Create your Vinkius account to connect Ellie Planner to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Entire Project History

LlamaIndex doesn't just call a tool; it learns from the output. It can run `list_tasks` for all your projects and feed the results directly into a vector index. Your project data becomes a long-term, searchable memory for your agent. Now you can find tasks based on what they mean, not just keywords. Ask about 'marketing efforts for the Q3 launch,' and the agent will find relevant tasks even if they don't contain those exact words.

Query Your Tasks in Natural Language

Stop guessing at filters. Just ask your agent, 'What are we working on for the beta release?' It queries the index it built from your Ellie Planner tasks and gives you a direct answer, grounded in real data. This is how you build a RAG application that uses your own project history as its source of truth. Your agent can `get_task` details to provide context, ensuring its answers are accurate and not just plausible hallucinations.

A Grounded LlamaIndex Agent

The `McpToolSpec` is the bridge between your data and your agent. It gives LlamaIndex a live connection to all the Ellie Planner tools, including `create_task` and `update_task`. This MCP Server is more than just a data source. Your RAG application can now do more than just answer questions. It can find relevant information in your index and then take action in Ellie Planner, like creating a follow-up task based on its findings.

Setup guide

Set up Ellie Planner MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Ellie Planner MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Ellie Planner tools.",
)
response = await agent.run("List recent Ellie Planner data")

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 LlamaIndex

First, use the `McpToolSpec` to load the Ellie Planner tools. Then, use a data loader to run `list_tasks` and ingest the results into your vector index. Your agent can now query this index to answer questions.

Yes. You configure it to fetch tasks using `list_tasks` and `get_task`, then it builds a local or remote vector index. All subsequent searches from your agent use this index for fast, semantic retrieval.

It is. Once the `McpToolSpec` provides the tools to your agent, it can call `update_task` just like any other function. For example, an agent could find overdue tasks and automatically add a 'Follow-up' label.

The MCP Server exposes the Ellie Planner functions in a standard format. The `McpToolSpec` in LlamaIndex reads this standard and converts the functions into tools the agent can use directly for both data indexing and taking action.

LlamaIndex processes your task content—including titles, descriptions, and labels—to create its search index. This index is stored in the vector database you configure. The security of your task data depends entirely on the security of your chosen vector store.

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