MCP App Store
by KeenEthics

Overview

StockLens scores stocks every night across five domains: Fundamental, Technical, Risk, Sentiment and Macro. Ask about a company and get its latest composite score and rating, the domain scores behind it, the named signals that most shaped the reading (up to three, each with its evidence), the business-model lens where one applies, and any domain that was not scored in it. Name several companies to compare them. Find your next idea instead of checking one ticker at a time. Discover Stocks screens the companies StockLens scores by region, exchange, sector, industry, market cap or volume, sorted by market cap, volume, ticker or a StockLens score. See where a portfolio stands: its average score and rating, its change over 7 and 30 nights, its biggest movers over 7 nights and its largest sector. Add or remove companies by asking, or add a list of up to 100 after a preview you approve. When one company matters most, run a full analysis: each domain's score, grade and contribution, written domain summaries and a synthesis, and a saved report on stocklens.com. StockLens scores listings nightly on 23 exchanges in North America, Europe and Asia-Pacific; not every listed company is scored, and macro context is drawn from the United States, Canada, the eurozone, the United Kingdom, Switzerland and Japan. It does not score ETFs, funds, indices, options or currencies. Without an account, scores answer for the 600 largest companies by market value; a signed-in account also reaches any company in its own portfolios. Every score carries the date it was computed. Try: - "How does NVDA score on StockLens?" - "Show me the five highest-scored Technology stocks on NASDAQ" - "Add AMZN, NFLX and NVDA to my StockLens portfolio, and show me the preview first" Sign in with your StockLens account for analyses, screening and portfolios. StockLens never places a trade. For informational and educational purposes only, not investment advice.

Tools

add_to_watchlist

ChatGPT
Add one company to the authenticated user's default StockLens portfolio as a company they follow, so its score stays readable here. Call it only when the person has asked for it or agreed to an offer. If the portfolio is already at the limit of the person's current plan, the result says so. After an add the person accepted from a get_market_summary offer, call get_market_summary again to answer their question. Does NOT execute trades, does NOT record a holding or transaction, and does NOT accept more than one ticker per call.

add_to_watchlist_batch

ChatGPT
Add a list of companies the person gave you, up to 100 rows, to one of their StockLens portfolios, in two calls. First call with confirm false: nothing is added and every row returns its outcome. Relay summary_line and message, then every row that is not a plain add, grouped by outcome, and name the plain adds in one line; name the portfolio only when portfolio_count is above 1. Ask which rows to add. Then call with confirm true, the preview_id, the same rows, the same portfolio and the confirmed_indexes the person approved. Send only rows the person gave you. For an ambiguous row, ask which listing using its candidates; never pick one. Add a not_covered row only if the person asks for it. A changed list or a different portfolio needs a new preview; preview_mismatch means the preview expired or no longer matches, so preview again. Without portfolio_id or portfolio_name it uses the default portfolio. It does not trade, record holdings or move money.

discover_stocks

ChatGPT
Screen the companies StockLens scores nightly by region, exchange, sector, industry, market-cap band and trading volume, sorted by one of the six StockLens scores or by market cap, volume, popularity or ticker, and return the top or bottom N. Use it for any top N, best, worst, highest, lowest or filtered request across the companies StockLens scores, and never build such a list from get_market_summary or general knowledge; to compare only companies the person names, call get_market_summary for each instead. It has no valuation, price-target or growth filter; say so rather than calling a score sort one. status ranked means the requested order was used. browse_substituted means a score order was asked for and market-cap order with scores hidden was returned, so never describe those rows as ranked by score. locked means no companies are named; relay message verbatim. What the caller can sort and how far it reaches is in access_tier and reach_capped_at. Report only the rows returned. It does not trade and gives no personal recommendations.

fetch_analysis_result

ChatGPT
Return the progress or result of an analysis started with initiate_analysis, by its analysis_id. Each call returns the current state once and does not wait. While status is in_progress, check again only when the person asks, and no sooner than retry_after_seconds. A failed status is an answer; relay error_message. A complete result carries the composite score and rating word, the evidence word (Full, Core or Low), each domain's score, grade word and contribution (cornerstone, major, supporting or contextual), key strengths and challenges, and for a Plus Analysis a written narrative. Say how much a domain counts only with its contribution word, never as a number or share. It does not accept a ticker and does not rank companies.

get_market_summary

ChatGPT
One company's latest nightly StockLens score: the composite score (0 to 100) and its rating word, the domain scores with their grade words, the named signals that most shaped the reading (up to three, each with its evidence), the business-model lens where one applies, and any domain that was not scored in it. Use the rating word for the company and grade words only for a domain. A higher Risk score means a stronger risk posture and less downside concern. Without an account, scores answer for the 600 largest companies by market value; a signed-in account also reaches any company in its own portfolios. A result with a status other than scored is an answer, not an error; do not retry it unchanged. Relay its message; not_in_surface means the company is scored and outside the caller's reach, never that StockLens has no analysis. Then act on next_step: for ask_user, ask the person and call the named tool only if they agree; mention an offer on a scored result at most once per conversation. Every result carries freshness; a stale result is StockLens's last computed reading for that listing, not last night's, and should be quoted with its date. When freshness.requested_ticker is present, say which listing was served and what was asked. One ticker per call. To compare companies the person names, call it once for each. For any other top, best, worst or filtered request call discover_stocks, and never choose the companies for a ranking yourself.

get_portfolio_insights

ChatGPT
Retrieve StockLens analysis summaries for the authenticated user's watchlist. Returns available composite scores and grades for watchlisted stocks; either value may be absent when no completed score exists. Returns the full watchlist up to the capacity of the person's current plan; tier_limited says whether it was cut short. Use this to give users an overview of their portfolio's analytical health. Does NOT accept a ticker or filter arguments and does NOT rank or screen stocks outside the user's own watchlist; call discover_stocks for a market-wide ranked or filtered list.

initiate_analysis

ChatGPT
Start a full StockLens analysis of one company, only when the person asks for one. A new run may use one Analysis credit, or one Plus Analysis credit when depth is plus; Plus adds a written narrative and the result says if the person's plan does not include it. It returns an analysis_id at once and finishes asynchronously; fetch the result with fetch_analysis_result when the person asks for it. new_run_started and reused_existing say whether a recent matching analysis was reused. One ticker per call. It does not rank or compare companies, and does not trade or move money.

ping

ChatGPT
Health check. Returns pong.

remove_from_watchlist

ChatGPT
Remove one company from the authenticated user's default StockLens portfolio. Does NOT execute trades and does NOT delete a recorded holding or its transactions; a holding with recorded transactions cannot be removed through this tool. Does NOT accept more than one ticker per call.

add_to_watchlist

Claude
Add one company to the authenticated user's default StockLens portfolio as a company they follow, so its score stays readable here. Call it only when the person has asked for it or agreed to an offer. If the portfolio is already at the limit of the person's current plan, the result says so. After an add the person accepted from a get_market_summary offer, call get_market_summary again to answer their question. Does NOT execute trades, does NOT record a holding or transaction, and does NOT accept more than one ticker per call.

add_to_watchlist_batch

Claude

discover_stocks

Claude
Screen the companies StockLens scores nightly by region, exchange, sector, industry, market-cap band and trading volume, sorted by one of the six StockLens scores or by market cap, volume, popularity or ticker, and return the top or bottom N. This is the only StockLens tool that ranks or compares companies: use it for any top N, best, worst, highest, lowest or filtered request, and never build such a list from get_market_summary or general knowledge. It has no valuation, price-target or growth filter; say so rather than calling a score sort one. status ranked means the requested order was used. browse_substituted means a score order was asked for and market-cap order with scores hidden was returned, so never describe those rows as ranked by score. locked means no companies are named; relay message verbatim. What the caller can sort and how far it reaches is in access_tier and reach_capped_at. Report only the rows returned. It does not trade and gives no personal recommendations.

fetch_analysis_result

Claude
Return the progress or result of an analysis started with initiate_analysis, by its analysis_id. Each call returns the current state once and does not wait. While status is in_progress, check again only when the person asks, and no sooner than retry_after_seconds. A failed status is an answer; relay error_message. A complete result carries the composite score and rating word, the evidence word (Full, Core or Low), each domain's score, grade word and contribution (cornerstone, major, supporting or contextual), key strengths and challenges, and for a Plus Analysis a written narrative. Say how much a domain counts only with its contribution word, never as a number or share. It does not accept a ticker and does not rank companies.

get_market_summary

Claude
One company's latest nightly StockLens score: the composite score (0 to 100) and its rating word, the domain scores with their grade words, the named signals that most shaped the reading (up to three, each with its evidence), the business-model lens where one applies, and any domain that was not scored in it. Use the rating word for the company and grade words only for a domain. A higher Risk score means a stronger risk posture and less downside concern. Without an account, scores answer for the 600 largest companies by market value; a signed-in account also reaches any company in its own portfolios. A result with a status other than scored is an answer, not an error; do not retry it unchanged. Relay its message; not_in_surface means the company is scored and outside the caller's reach, never that StockLens has no analysis. Then act on next_step: for ask_user, ask the person and call the named tool only if they agree; mention an offer on a scored result at most once per conversation. Every result carries freshness; a stale result is StockLens's last computed reading for that listing, not last night's, and should be quoted with its date. When freshness.requested_ticker is present, say which listing was served and what was asked. One ticker per call. It does not rank, sort or list companies: for any top, best, worst or filtered request call discover_stocks, and never build a ranking from repeated calls.

get_portfolio_insights

Claude
Retrieve StockLens analysis summaries for the authenticated user's watchlist. Returns available composite scores and grades for watchlisted stocks; either value may be absent when no completed score exists. Returns the full watchlist up to the capacity of the person's current plan; tier_limited says whether it was cut short. Use this to give users an overview of their portfolio's analytical health. Does NOT accept a ticker or filter arguments and does NOT rank or screen stocks outside the user's own watchlist; call discover_stocks for a market-wide ranked or filtered list.

initiate_analysis

Claude
Start a full StockLens analysis of one company, only when the person asks for one. A new run may use one Analysis credit, or one Plus Analysis credit when depth is plus; Plus adds a written narrative and the result says if the person's plan does not include it. It returns an analysis_id at once and finishes asynchronously; fetch the result with fetch_analysis_result when the person asks for it. new_run_started and reused_existing say whether a recent matching analysis was reused. One ticker per call. It does not rank or compare companies, and does not trade or move money.

ping

Claude
Health check. Returns pong.

remove_from_watchlist

Claude
Remove one company from the authenticated user's default StockLens portfolio. Does NOT execute trades and does NOT delete a recorded holding or its transactions; a holding with recorded transactions cannot be removed through this tool. Does NOT accept more than one ticker per call.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps