September 4, 2026
Asking Claude About My Screeners: an MCP Diary
A workflow diary: querying the Hot Prospects screener from inside Claude via MCP surfaced Elastic at $83.74 on a Friday. The stock stood 14.8% higher a week later.
Last diary entry for this week, and it is the strangest workflow of the four, because it does not involve the website, the API console, or an alert email. It involves a chat window that is not even ours.
Friday, one prompt
Since StockMarketScan speaks MCP, any AI client that supports the protocol, Claude Desktop in my case, can query the screeners directly in a conversation. My Friday, August 28 prompt was one sentence: pull today's Hot Prospects list, keep only software names, and tell me which ones look like they are recovering rather than extending.
The agent called the screener tool, got the day's list, filtered it, and came back with a short table. The name that stood out was Elastic (ESTC) at $83.74, and the agent's framing was the interesting part: it noted, from the data itself, that ESTC had been on the same list at $85.94 on Monday the 24th, meaning the stock re-qualified for a momentum list while trading lower than a week before. Momentum criteria being met on a falling price is a compression pattern worth a look, and I would not have caught the nuance scrolling by hand.
The week after
| Date | Event | Price | Change vs Aug 28 |
|---|---|---|---|
| Mon Aug 24 | On Hot Prospects, first pass | $85.94 | +2.6% above the entry |
| Fri Aug 28 | Re-qualified lower; the MCP session | $83.74 | 0.0% |
| Mon Aug 31 | Single-session repricing, re-listed | $99.44 | +18.8% |
| Thu Sep 3 | The give-back low | $89.58 | +7.0% |
| Fri Sep 4 | Where it stands as this entry is written | $96.13 | +14.8% |
Monday's session did the loud part, a repricing from $83.74 to $99.44 in one go. The week since has been the usual argument with gravity: down to $89.58 by Thursday, back to $96.13 on Friday, and the stock re-qualified for Hot Prospects on both August 31 and September 4. Net result, one week after the Friday prompt: +14.8%.
Why route this through an AI at all
Fair question, since the list is one click away in the browser. Three answers from actually doing it. First, filtering and cross-referencing happen in the same breath as retrieval; "software names that are recovering" is not a filter the UI has, but it is a sentence. Second, the agent reads the whole row, so nuances like re-qualifying at a lower price surface without me hunting for them. Third, the same conversation can pull chart patterns and market breadth over the same MCP server and reason across all of it. The screeners stay the source of truth; the agent is a faster pair of eyes on them.
The honest footnote
Same disclosure as every entry in this series: this example is here because it worked, the Monday repricing was not predicted by anyone or anything in this workflow, and a week is a week. What repeats is that a one-sentence prompt turned a 415-name list into one considered candidate in under a minute, with the reasoning shown.
Related Resources
- MCP Server to connect the screeners to Claude, Cursor or Continue.
- Hot Prospects Screener for the list itself.
- An AI Research Workflow for a deeper MCP setup.
This article is a retrospective review of historical data for educational purposes only. It is not investment advice, the example was selected after the fact because it performed well, and screener appearances are data points, not recommendations.