Most dividend tools give you a\u00a0table.<\/p>\n
Numbers in columns. Yield percentages. Payout ratios. A filter you drag left or\u00a0right.<\/p>\n
What they don\u2019t give you is judgment.<\/p>\n
They can\u2019t tell you why a 7% yield might be a trap. They can\u2019t flag that a company\u2019s payout ratio has been climbing for six consecutive quarters. They won\u2019t notice that a dividend that looks rock-solid today is sitting on a balance sheet that started deteriorating twelve months\u00a0ago.<\/p>\n
That distinction\u200a\u2014\u200abetween data and reasoning\u200a\u2014\u200ais exactly what this experiment was\u00a0about.<\/p>\n
I connected Claude to EODHD\u2019s financial data API, gave it a list of dividend-paying stocks, and asked it to build a screener from scratch. No spreadsheet. No Python script. No pre-built tool.<\/p>\n
Just a conversation. And live\u00a0data.<\/p>\n
If you\u2019re:<\/p>\n
building income-focused portfolio tools,managing your own dividend strategy and tired of switching between screeners,or evaluating what AI agents can actually do with institutional-grade financial data,<\/p>\n
This is worth\u00a0reading.<\/p>\n
Here\u2019s what a typical investor does when they want to screen for dividend\u00a0stocks:<\/p>\n
Go to a screener. Set yield above 3%. Filter by sector. Sort by payout ratio. Export to Excel. Open a second tab for the income statement. A third for the balance sheet history. Maybe a fourth to check if the dividend was cut in the last five\u00a0years.<\/p>\n
Then they start the actual analysis.<\/p>\n
The tool gave them a list. The thinking still happens manually, in isolation, without any connection between the data\u00a0points.<\/p>\n
That\u2019s the\u00a0gap.<\/p>\n
A high yield and a low payout ratio tell you something. But they don\u2019t tell you everything. A company can show a healthy payout ratio today while its free cash flow has been shrinking for eight quarters. The number looks fine. The trend\u00a0doesn\u2019t.<\/p>\n
Most screeners show you the snapshot. They don\u2019t show you the\u00a0movie.<\/p>\n
MCP stands for Model Context Protocol\u200a\u2014\u200aan open standard introduced by Anthropic.<\/p>\n
Think of it as USB-C for AI. Before MCP, connecting an AI model to an external data source required custom integration code for every single API. A different script, a different auth flow, a different data format. For each\u00a0one.<\/p>\n
MCP replaces all of that with a single standard. One connection. Full\u00a0access.<\/p>\n
Instead of the AI guessing based on training data, it can now query APIs, retrieve live data, and execute workflows in real time\u200a\u2014\u200adirectly from the conversation.<\/p>\n
Most AI tools have a hard ceiling: their knowledge cutoff.<\/p>\n
Ask Claude about NVIDIA\u2019s earnings from two years ago\u200a\u2014\u200ait knows. Ask it about last quarter\u2019s free cash flow\u200a\u2014\u200ait guesses. And confident-sounding guesses built on stale data are worse than no answer at all, because they look credible.<\/p>\n
Without MCP, a typical analyst workflow looks like\u00a0this:<\/p>\n
Open a screener for initial filteringExport to Excel, reformat\u00a0columnsOpen a second tab for income statementsA third for dividend\u00a0historyA fourth for analyst consensus<\/p>\n
Then start the actual analysis.<\/p>\n
The bottleneck isn\u2019t intelligence. It\u2019s infrastructure.<\/p>\n
With an MCP-connected data source like EODHD, the flow collapses into a single\u00a0layer:<\/p>\n
1. You ask a question<\/strong> in natural language\u200a\u2014\u200a\u201cWhich of these stocks has the safest dividend?\u201d<\/p>\n 2. Claude interprets the intent<\/strong>\u200a\u2014\u200ait understands you need yield, payout ratio, FCF coverage, and dividend\u00a0history.<\/p>\n 3. Claude selects the right MCP tools<\/strong>\u200a\u2014\u200ait calls EODHD\u2019s endpoints automatically, without you specifying which\u00a0ones.<\/p>\n 4. EODHD returns live data<\/strong>\u200a\u2014\u200asourced directly from exchanges and regulatory filings, not cached or estimated.<\/p>\n 5. Claude synthesizes and responds<\/strong>\u200a\u2014\u200awith structured analysis, not a table of raw\u00a0numbers.<\/p>\n The analyst\u2019s job shifts from data gathering to judgment. Which is where their expertise actually\u00a0lives.<\/p>\n EODHD\u200a\u2014\u200aMCP<\/p>\n Not all financial data APIs are equal\u200a\u2014\u200aand the quality gap matters more when AI is doing the reasoning.<\/p>\n EODHD provides:<\/p>\n 150,000+ tickers<\/strong> across 70+ exchangesFull financial statements<\/strong>\u200a\u2014\u200aincome, balance sheet, cash\u00a0flowDividend history<\/strong> going back decades, adjusted for corporate actionsAnalyst estimates<\/strong> and consensus dataInsider transactions<\/strong> sourced from regulatory filingsMacro indicators<\/strong> for cross-dataset analysisNative MCP server<\/strong>\u200a\u2014\u200aone connection, full dataset access in\u00a0Claude<\/p>\n When Claude reasons on EODHD data, it isn\u2019t estimating. It\u2019s fetching. That distinction is what makes the output trustworthy enough to act\u00a0on.<\/p>\n Before getting into the session, one point\u00a0matters:<\/p>\n The quality of the data determines the quality of the analysis.<\/p>\n EODHD<\/strong> provides institutional-grade financial data through a clean REST API\u200a\u2014\u200aend-of-day prices, full financial statements, dividend history, earnings estimates, and fundamentals for 150,000+ tickers across 70+ exchanges. Data sourced directly from exchanges and regulatory filings, not scraped or aggregated through unofficial feeds.<\/p>\n When Claude reasons on EODHD data, it isn\u2019t working with stale snapshots or estimated figures. It\u2019s working with the same underlying data infrastructure that powers serious financial tools.<\/p>\n That distinction is what makes the screener session below useful\u200a\u2014\u200aand not just a\u00a0demo.<\/p>\n \ud83d\udc49 Start free with EODHD here<\/strong>\u200a<\/a>\u2014\u200athe free tier includes historical EOD data and fundamentals access.<\/p>\n EODHD offers a native MCP server. Once connected, Claude has direct access to EODHD\u2019s full dataset in natural language\u200a\u2014\u200ano code, no custom integration.<\/p>\n Step 1\u200a\u2014\u200aGet your EODHD API\u00a0key<\/strong><\/p>\n Create an account at eodhd.com. The free tier covers historical data and fundamentals\u200a\u2014\u200aenough to replicate everything in this\u00a0article.<\/p>\n Step 2\u200a\u2014\u200aAdd it to\u00a0Claude<\/strong><\/p>\n In Claude.ai: Settings \u2192 Connectors \u2192 Add custom connector \u2192 paste your EODHD MCP URL \u2192 name it \u201cEODHD\u201d \u2192\u00a0Add.<\/p>\n Start a new chat. EODHD\u2019s tools are now available to Claude automatically.<\/p>\n Add your API\u00a0key<\/p>\n tue url have the following aspect: https:\/\/mcpv2.eodhd.dev\/v2\/mcp<\/a><\/p>\n You will see the list of data endpoints<\/strong><\/p>\n I gave Claude a starting list of ten dividend-paying stocks across different sectors: JNJ, KO, PG, T, MO, ABBV, PEP, VZ, O,\u00a0XOM<\/strong>.<\/p>\n Classic income portfolio candidates. Some with decades of consecutive dividend increases. Some with yields high enough to raise questions.<\/p>\n Then I started\u00a0asking.<\/p>\n Claude pulled current yield data and payout ratios from EODHD for all ten tickers simultaneously, then cross-referenced each against free cash flow coverage\u200a\u2014\u200aa step I didn\u2019t ask\u00a0for.<\/p>\n The output wasn\u2019t a sorted table. It was a tiered analysis:<\/p>\n Tier 1\u200a\u2014\u200aHigh yield, strong coverage:<\/strong> Altria (MO) and Realty Income (O) topped the yield ranking, but with important caveats. MO\u2019s payout ratio is high by conventional standards\u200a\u2014\u200ayet its free cash flow generation has consistently covered the dividend with room to spare. O structures its dividends around AFFO, not earnings, which changes the payout ratio math entirely.<\/p>\n Tier 2\u200a\u2014\u200aModerate yield, very safe:<\/strong> KO, PG, PEP. Lower yields but fortress-level dividend history. Claude flagged all three as Dividend Kings without me asking\u200a\u2014\u200apulling that context from the fundamentals data.<\/p>\n Tier 3\u200a\u2014\u200aHigh yield, worth watching:<\/strong> T and VZ both show elevated yields driven partly by compressed valuations. Claude noted that both have been managing high debt loads while maintaining dividends\u200a\u2014\u200aa combination that warrants closer monitoring, not immediate exclusion.<\/p>\n What would normally take an hour of tab-switching took about 12\u00a0seconds.<\/p>\n EODHD MCP real data with\u00a0claude<\/p>\n Claude fetched EODHD\u2019s full dividend history for MO, T, and VZ going back ten years, organized it chronologically, and flagged every year where the dividend was held flat or\u00a0reduced.<\/p>\n The result surfaced something worth knowing: AT&T cut its dividend in 2022 following the WarnerMedia spinoff\u200a\u2014\u200aa move that significantly reset its income profile. Claude noted this explicitly, with the quarter and percentage reduction, sourced directly from EODHD\u2019s dividend\u00a0records.<\/p>\n Not guessed. Not approximated. Fetched.<\/p>\n This is the kind of signal that gets buried when you\u2019re looking at current yield alone. A stock that cut its dividend three years ago and has since stabilized is a very different investment than one with an unbroken 30-year record\u200a\u2014\u200aeven if the current yield looks identical.<\/p>\n Claude pulled quarterly cash flow statements from EODHD for KO, PG, and PEP, calculated the free cash flow payout ratio for each quarter, and plotted the trend directionally.<\/p>\n The analysis on Coca-Cola was particularly sharp: strong and stable FCF coverage throughout the period, with coverage ratios consistently above 70%\u200a\u2014\u200ahealthy for a mature consumer staples company with predictable cash\u00a0flows.<\/p>\n Procter & Gamble showed a similar pattern, with one quarter of compression that Claude correctly attributed to elevated capex during a facility expansion cycle\u200a\u2014\u200avisible in the capital expenditure line of the same cash flow statement.<\/p>\n It didn\u2019t just answer the question. It explained the\u00a0anomaly.<\/p>\n Claude synthesized everything it had already pulled\u200a\u2014\u200adividend history, FCF coverage trends, payout sustainability, debt levels\u200a\u2014\u200aand built a structured argument for five positions.<\/p>\n The recommendation: KO, PG, PEP, O,\u00a0ABBV.<\/strong><\/p>\n The reasoning for each exclusion was explicit:<\/p>\n T:<\/strong> dividend cut history + ongoing debt reduction pressureVZ:<\/strong> similar concerns, lower FCF growth trajectoryMO:<\/strong> sustainable today, but long-term business model risk warrants a separate\u00a0decisionXOM:<\/strong> dividend is sound, but commodity exposure conflicts with an income-stability mandateJNJ:<\/strong> recent Kenvue spinoff changes the historical comparability of dividend\u00a0data<\/p>\n That\u2019s the kind of structured reasoning that goes into a real portfolio construction decision. Not a list of tickers with yield percentages attached.<\/p>\n The standard workflow for dividend analysis involves at least four separate tools: a screener for initial filtering, a financial data source for statements, a dividend history tracker, and something to cross-reference analyst ratings or macro\u00a0context.<\/p>\n Each tool answers one question. Connecting the answers is manual\u00a0work.<\/p>\n With EODHD<\/strong><\/a> + Claude, the connection happens in the conversation. You ask a question that spans multiple data types\u200a\u2014\u200ayield, history, FCF, coverage ratio, sector context\u200a\u2014\u200aand get a synthesized answer, not four separate outputs you have to reconcile yourself.<\/p>\n The cognitive load shift is significant.<\/p>\n You move from gathering<\/em> to judging<\/em>. The data assembly is automated. The actual investment thinking is what you\u2019re left\u00a0with.<\/p>\n Once EODHD is connected, you can\u00a0run:<\/p>\n Dividend growth screeners<\/strong>\u200a\u2014\u200aidentify companies with 10+ consecutive years of dividend increases, filtered by sector and payout ratio\u00a0rangeYield trap detectors<\/strong>\u200a\u2014\u200aflag stocks where high yield correlates with deteriorating FCF or rising\u00a0debtDividend safety scores<\/strong>\u200a\u2014\u200abuild a composite of payout ratio, FCF coverage, and dividend history into a single reliability rankingPre-earnings dividend risk checks<\/strong>\u200a\u2014\u200abefore a quarterly report, pull the FCF trend and ask Claude whether the dividend coverage is at\u00a0riskSector income comparisons<\/strong>\u200a\u2014\u200a\u201cCompare average dividend yield and payout ratios across consumer staples, utilities, and\u00a0REITs\u201d<\/p>\n The infrastructure is already there. The data is live. The interface is a question.<\/p>\n Most dividend investors don\u2019t lack access to\u00a0data.<\/p>\n They lack time to connect\u00a0it.<\/p>\n That\u2019s the problem this setup solves\u200a\u2014\u200aand why the screener you build in a conversation is more useful than the one you build in a spreadsheet.<\/p>\n \ud83d\udc49 Get started with EODHD here<\/strong>\u200a<\/a>\u2014\u200aclean dividend history, full fundamentals, and MCP support for AI\u00a0agents.<\/p>\n Looking for technical content for your company? I can help\u200a\u2014\u200a<\/em>LinkedIn<\/em><\/a> \u00b7 <\/em>kevinmenesesgonzalez@gmail.com<\/em><\/a><\/p>\n I Asked Claude to Build Me a Dividend Screener Using EODHD \u2014 Here\u2019s What It Found<\/a> was originally published in Coinmonks<\/a> on Medium, where people are continuing the conversation by highlighting and responding to this story.<\/p>","protected":false},"excerpt":{"rendered":" Most dividend tools give you a\u00a0table. Numbers in columns. Yield percentages. Payout ratios. A filter you drag left or\u00a0right. What they don\u2019t give you is judgment. They can\u2019t tell you why a 7% yield might be a trap. They can\u2019t flag that a company\u2019s payout ratio has been climbing for six consecutive quarters. They won\u2019t […]<\/p>\n","protected":false},"author":0,"featured_media":163625,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[],"class_list":["post-163624","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-interesting"],"_links":{"self":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/posts\/163624"}],"collection":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=163624"}],"version-history":[{"count":0,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/posts\/163624\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/media\/163625"}],"wp:attachment":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=163624"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=163624"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=163624"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Why EODHD Specifically<\/h4>\n
Why EODHD Changes the\u00a0Equation<\/h3>\n
The Setup: EODHD + Claude in 2\u00a0Steps<\/h3>\n
The Session: Building the Screener in Conversation<\/h3>\n
Question 1: \u201cRank these ten stocks by dividend yield and tell me which ones look sustainable.\u201d<\/h3>\n
Question 2: \u201cShow me the 10-year dividend history for the three highest-yielding stocks and flag any cuts or\u00a0freezes\u201d<\/h3>\n
Question 3: \u201cFor the Dividend Kings in this list, pull the last 8 quarters of free cash flow and tell me if the dividend is getting harder to\u00a0cover\u201d<\/h3>\n
Question 4: \u201cIf I had to build a 5-stock dividend portfolio from this list focused on income stability\u200a\u2014\u200anot maximum yield\u200a\u2014\u200awhich would you\u00a0pick?\u201d<\/h3>\n
What This Changes for Income Investors<\/h3>\n
What You Can Build From\u00a0Here<\/h3>\n