Turning ChatGPT into my stock analyst using Rube MCP

ChatGPT recently introduced MCP support for Paid tier user, and being a developer, I had to test it. So, I went ahead and created a Stock Analyser to help me find the right stocks.

In the journey, I devised a simple flow and chose Rube as my partner & this blog explores my struggles, learnings and build in depth.

So, let’s begin with a motivation!

Motivation

One of the pains point I often face is finding the right stocks and investing at the right time. Even with LLM, there was too much mess:

• Prompting the ChatGPT,

• Generating responses in a structured way,

• Verifying the data by switching back and forth between Yahoo Finance & ChatGPT Response

• Copying and pasting the legit entries,

Sometimes I used data connectors/ apps (Google Sheets Add-on, Zapier, Coupler) and APIs (IEX, Yahoo Finance, etc.), but connecting them was a pain, & all just messed things up.

So, I switched gears to Composio’s Rube, which aims to simplify all the problems I had.

To be honest, I was expecting the same painful experience, while using Composio & Rube, it was damn easy, let me show you the flow after a quick intro on rube (for beginners)

A Brief on Rube

Rube is a universal MCP (Model Context Protocol) for AI Agents.

Think of it as a bridge between AI models like ChatGPT and your favourite tools like Google Sheets, Search APIs, SQL databases,

Instead of building custom scripts or dealing with OAuth, SaaS APIs, Rube gives you instant access to 500+ apps, without worrying about authentication, tool selection, call and & right action selection and security.

For businesses, that means faster decisions. For developers, it means less boilerplate and more time building value.

But how does all this connect to solving the pain point we had when researching stocks?

Let’s look at the flow!

The Flow Shift with Rube & Composio

The flow is simple:

• Prompt ChatGPT for stock summaries and key metrics (I am going for SP500)

• Use Rube, which:

  • Checks the active environment, if not, prompts me to authenticate (oAuth)

  • Devises a plan for the given task - say, by step-by-step breakdown

  • Fetch the required tool, perform the tool / Api call, execute the step, and generate a structured response (Json)

  • Finally, normalise the response into rows and push the data directly into Google Sheets

• Share the live Sheet link with me.

• Additionally, can provide charts to visualise comparisons (didn’t find feasible, so left)

The benefit for me here was that,

Once prompted, I didn’t need to switch between ChatGPT responses, Financial Apps & Google Sheets.

Having understood the flow, let me show you how I built it and how you can too!

Step 1 - Connecting Rube to GPT

Note: To use rube, you need to have ChatGPT Plus plan at least.

Connecting Rube to GPT is straightforward:

• Head to ChatGPT Settings ⚙️

• Goto Connectors → Advanced Settings → Enable Developer Mode and toggle it on.

• Head back to Connectors and click the Create button beside it.

• Now fill in the details as follows:

  • Name: Rube

  • Description: Leave Blank

  • MCP Server URL: https://rube.app/mcp

  • Authentication: OAuth

  • Now accept> I trust this application and hit Create.

In a few seconds, you will be prompted to authenticate rube by logging in.

If you have an account, log in and select the workspace you want to use. Otherwise, create a new one and select the default workspace. This will be the environment Rube will look into!

By the end, you should have something similar 👇

Step 2 - Authenticating Apps in Rube

To ensure we are not prompted to authenticate, you can preregister them in the Rube. Let’s see how to do that.

Steps are super simple:

• Navigate to the Rube Dashboard. In case you face an error, make sure you are logged in.

• Go to the Marketplace and select the required apps for the job. -MCP Google Sheets.

• In the Google Sheets window:

  • Click on Enable App.

  • Select the scopes needed - basically the permissions

  • & Login using Composio oAuth (same top-notch security out of the box).

• For search, we can use the Composio Search / Yahoo Finance API. I went for later!

Apart from this, you can add 500+ tools. Here is what I use daily 👇

With this, we are now set to fire the Stock Analyser!

Step 3 - Fire Up Stock Analyser using ChatGPT & Rube

Before firing up, ensure you have developer mode enabled and the rube setup. If not, refer to step 1

Anyway’s. Let’s activate the rube. It's simple:

• Head to any chat window

• Click on ➕ button → More… → Developer Mode

• Besides Developer Mode, click Add Source & toggle on Rube (or the name you defined in step 1)

Now we are all set.

It's a good practice to check if all connected tools are available or not, but personal preference here. To check you can prompt rube: What all tools do you have access too

To kick things off, in the same chat, paste the following prompt and execute:

fetch a structured S&P 500 constituents list from a reliable finance API/web source (e.g., S&P index constituents from an authoritative provider or a well-structured data source) and then fully populate Top 100 (will fill Market Cap, YTD%, Sector myself).

& let the Rube & Composio handle the rest. Here is what it looks like in practice 👇

In case you want a reference, here is the file it generated: Top S&P 100 Stocks - Market Cap (Top 100)

Now let’s look at what this workflow actually delivers for an individual & a business.

The Benefits

Notice

Once I gave the prompt, I didn’t have to do anything, except for an occasional confirmation request by ChatGPT. (for security).

Also, I saved myself the hassle of copy-pasting, defining APIs and a custom connector; all was handled by the Rube & Composio, converting my evening pain into a relaxed one.

For businesses, this translates to:

• Faster insights: No more manual copy-paste—stock metrics flow directly into Google Sheets in seconds.

• Consistent accuracy: Automated normalisation reduces human error in financial analysis.

• Collaborative dashboards: Live Sheets with charts can be instantly shared across teams via Slack or Gmail.

• Scalable workflows: The same pipeline can track 10 stocks today or 1,000 tomorrow without extra effort, all using natural language

• Focus on decisions, not plumbing: Analysts and ops spend time interpreting data, not wrangling it.

Also, business and individual devs can use this template and extend it for scenarios like:

• Competitor tracking: Automatically pull ChatGPT summaries of competitor launches or funding news into Google Sheets.

• Marketing research: Export campaign keyword ideas or audience insights from ChatGPT straight into Sheets for quick analysis.

• Sales prospecting: Generate and append lead lists (company, contact, role) into Sheets for the RevOps team.

• Customer feedback: Summarise survey responses or support tickets into a structured Sheet for product teams.

• Project dashboards: Collect API or ChatGPT status updates and auto-push them into Sheets for real-time team visibility.

I hope you got an idea of how it can help you & others, including business.

So, all good, but what’s the Final take?

Conclusion

Google Sheets isn’t going anywhere, but the effort used to perform data wrangling is!

With this ChatGPT data pipeline workflow (Rube + ChatGPT), you can unlock an endless set of recipes: research → Sheet, API → Sheet, CSV → Sheet. Each one replaces friction with flow.

Start small, extend it to your use case, and see how much time you save. The future of financial (and business) ops is not about crunching data - it’s about making better decisions faster.

So, what are you waiting for, get started building with exploring possibility with Rube.