Picture by Ideogram
Most of my days as an information scientist appear like this:
- Stakeholder: “Are you able to inform us how a lot we made in promoting income within the final month and what number of that got here from search advertisements?”
- Me: “Run an SQL question to extract the information and hand it to them.”
- Stakeholder: “I see. What’s our income forecast for the following 3 years?”
- Me: “Consolidate information from a number of sources, converse to the finance crew, and construct a mannequin that forecasts income.”
Duties just like the above are advert hoc requests from enterprise stakeholders. They take round 3–5 hours to finish and are normally unrelated to the core venture I am engaged on.
When data-related questions like these are available, they typically require me to push the deadlines of present tasks or work further hours to get the job performed. And that is the place AI is available in.
As soon as AI fashions like ChatGPT and Claude have been made out there, the crew’s effectivity improved, as did my skill to reply to advert hoc stakeholder requests. AI dramatically diminished the time I spent writing code, producing SQL queries, and even collaborating with totally different groups for required data. Moreover, after AI code assistants like Cursor have been built-in with our codebases, effectivity beneficial properties improved even additional. Duties just like the one I simply defined above might now be accomplished twice as quick as earlier than.
Just lately, when MCP servers began gaining reputation, I assumed to myself:
Can I construct an MCP that automates these information science workflows additional?
I spent two days constructing this MCP server, and on this article, I’ll break down:
- The outcomes and the way a lot time I’ve saved with my information science MCP
- Sources and reference supplies used to create the MCP
- The essential setup, APIs, and providers I built-in into my workflow
# Constructing a Knowledge Science MCP
For those who do not already know what an MCP is, it stands for Mannequin Context Protocol and is a framework that lets you join a big language mannequin to exterior providers.
This video is a good introduction to MCPs.
// The Core Drawback
The issue I needed to resolve with my new information science MCP was:
How do I consolidate data that’s scattered throughout numerous sources and generate outcomes that may instantly be utilized by stakeholders and crew members?
To perform this, I constructed an MCP with three elements, as proven within the flowchart under:
Picture by Writer | Mermaid
// Element 1: Question Financial institution Integration
As a data base for my MCP, I used my crew’s question financial institution (which contained questions, a pattern question to reply the query, and a few context in regards to the tables).
When a stakeholder asks me a query like this:
What proportion of promoting income got here from search advertisements?
I now not need to look via a number of tables and column names to generate a question. The MCP as an alternative searches the question financial institution for the same query. It then beneficial properties context in regards to the related tables it ought to question and adapts these queries to my particular query. All I have to do is name the MCP server, paste in my stakeholder’s request, and I get a related question in a couple of minutes.
// Element 2: Google Drive Integration
Product documentation is normally saved in Google Drive—whether or not it is a slide deck, doc, or spreadsheet.
I related my MCP server to the crew’s Google Drive so it had entry to all our documentation throughout dozens of tasks. This helps shortly extract information and reply questions like:
Are you able to inform us how a lot we made in promoting income within the final month?
I additionally listed these paperwork to extract particular key phrases and titles, so the MCP merely has to undergo the key phrase checklist based mostly on the question quite than accessing a whole bunch of pages without delay.
For instance, if somebody asks a query associated to “cell video advertisements,” the MCP will first search via the doc index to determine probably the most related information earlier than trying via them.
// Element 3: Native Doc Entry
That is the best element of the MCP, the place I’ve an area folder that the MCP searches via. I add or take away information as wanted, permitting me so as to add my very own context, data, and directions on prime of my crew’s tasks.
# Abstract: How My Knowledge Science MCP Works
This is an instance of how my MCP at present works to reply advert hoc information requests:
- A query is available in: ”What number of video advert impressions did we serve in Q3, and the way a lot advert demand do we have now relative to produce?”
- The doc retrieval MCP searches our venture folder for “Q3,” “video,” “advert,” “demand,” and “provide,” and finds related venture paperwork
- It then retrieves particular particulars in regards to the Q3 video advert marketing campaign, its provide, and demand from crew paperwork
- It searches the question financial institution for comparable questions on advert serves
- It makes use of the context obtained from the paperwork and question financial institution to generate an SQL question about Q3’s video marketing campaign
- Lastly, the question is handed to a separate MCP that’s related to Presto SQL, which is robotically executed
- I then collect the outcomes, overview them, and ship them to my stakeholders
# Implementation Particulars
Right here is how I applied this MCP:
// Step 1: Cursor Set up
I used Cursor as my MCP consumer. You may set up Cursor from this hyperlink. It’s primarily an AI code editor that may entry your codebase and use it to generate or modify code.
// Step 2: Google Drive Credentials
Nearly all of the paperwork utilized by this MCP (together with the question financial institution) have been saved in Google Drive.
To present your MCP entry to Google Drive, Sheets, and Docs, you may have to arrange API entry:
- Go to the Google Cloud Console and create a brand new venture.
- Allow the next APIs: Google Drive, Google Sheets, Google Docs.
- Create credentials (OAuth 2.0 consumer ID) and save them in a file known as
credentials.json.
// Step 3: Set Up FastMCP
FastMCP is an open-source Python framework used to construct MCP servers. I adopted this tutorial to construct my first MCP server utilizing FastMCP.
(Notice: This tutorial makes use of Claude Desktop because the MCP consumer, however the steps are relevant to Cursor or any AI code editor of your alternative.)
With FastMCP, you possibly can create the MCP server with Google integration (pattern code snippet under):
@mcp.software()
def search_team_docs(question: str) -> str:
"""Search crew paperwork in Google Drive"""
drive_service, _ = get_google_services()
# Your search logic right here
return f"Looking for: {question}"
// Step 4: Configure the MCP
As soon as your MCP is constructed, you possibly can configure it in Cursor. This may be performed by navigating to Cursor’s Settings window → Options → Mannequin Context Protocol. Right here, you may see a bit the place you possibly can add an MCP server. If you click on on it, a file known as mcp.json will open, the place you possibly can embrace the configuration in your new MCP server.
That is an instance of what your configuration ought to appear like:
{
"mcpServers": {
"team-data-assistant": {
"command": "python",
"args": ["path/to/team_data_server.py"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "path/to/credentials.json"
}
}
}
}
After saving your modifications to the JSON file, you possibly can allow this MCP and begin utilizing it inside Cursor.
# Remaining Ideas
This MCP server was a easy facet venture I made a decision to construct to save lots of time on my private information science workflows. It is not groundbreaking, however this software solves my speedy ache level: spending hours answering advert hoc information requests that take away from the core tasks I am engaged on. I consider {that a} software like this merely scratches the floor of what is attainable with generative AI and represents a broader shift in how information science work will get performed.
The normal information science workflow is transferring away from:
- Spending hours discovering information
- Writing code
- Constructing fashions
The main focus is shifting away from hands-on technical work, and information scientists are actually anticipated to have a look at the larger image and clear up enterprise issues. In some instances, we’re anticipated to supervise product choices and step in as a product or venture supervisor.
As AI continues to evolve, I consider that the traces between technical roles will change into blurred. What is going to stay related is the ability of understanding enterprise context, asking the appropriate questions, deciphering outcomes, and speaking insights. In case you are an information scientist (or an aspiring one), there isn’t any query that AI will change the way in which you’re employed.
You could have two selections: you possibly can both undertake AI instruments and construct options that form this alteration in your crew, or let others construct them for you.
Natassha Selvaraj is a self-taught information scientist with a ardour for writing. Natassha writes on every thing information science-related, a real grasp of all information subjects. You may join together with her on LinkedIn or try her YouTube channel.
