Massive MCP. Find historical stock dividend payouts instantly.
Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
The `list_dividends` tool fetches full historical cash dividend records for any supported stock ticker. Your AI agent runs this function by accepting parameters like the ticker, date range, and required frequency (annual, quarterly).
This gives you a clean dataset of past payouts needed for deep financial modeling and equity research.
What your AI agents can do
List dividends
Retrieves historical cash dividend payouts for any specified stock ticker.
Your agent retrieves the full record of cash dividends for a specific stock ticker.
The tool lets you filter results to isolate special, recurring, or supplemental distributions based on dates.
You can query for consistency across different frequencies (e.g., quarterly vs. annual) to track payment patterns.
By providing the necessary payout data, your agent calculates dividend growth rates and historical yields.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 CompatibleWaiting for input…
Massive MCP Server: 1 Tool for Dividend Analysis
The single `list_dividends` tool lets you pull clean, structured data on past stock payouts and distribution history.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Massive on Vinkius019e38bdlist dividends
Retrieves historical cash dividend payouts for any specified stock ticker.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Massive, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Massive. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 1 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Manual dividend research sucks time.
Before MCP servers, checking a company's payout history meant opening multiple financial websites. You’d find annual reports here, quarterly data there, and sometimes the special payments were tucked away in a press release you had to manually read. It was hours of copy-pasting dates and amounts into Excel just to build a basic timeline.
Now, your agent handles it. You tell it: 'Give me the dividend history for AAPL.' The system runs `list_dividends`, pulls everything—special, regular, annual—and gives you one clean, structured list of payouts. It’s immediate.
Massive MCP Server: Massive's `list_dividends` tool.
You no longer have to piece together a payout history from half-dozen sources, each with different date formats and data schemas. The pain points around manual aggregation—the mismatched column headers, the missing special dividend records—are gone.
It’s simple: you ask your agent for historical dividends. It gets it right every time.
What you can do with this MCP connector
You're gonna run complex finance queries without ever needing to mess with an API key or a giant spreadsheet. This server hooks your AI client up to the raw historical payout data you need for deep equity research.
The list_dividends tool fetches full records of cash dividend payouts for any stock ticker you throw at it. Your agent runs this function, and it gives you a clean, exhaustive dataset of past company distributions needed for serious financial modeling. You're analyzing patterns here; you ain't just checking a number.
When you use list_dividends, your AI client retrieves the complete dividend history—every payment counts, whether it was a regular handout or some one-off special distribution. It grabs all cash payouts, so you get the full story on how much money companies are sending back to shareholders over time. You can track every recurring payout and even isolate those supplemental payments that throw off simple calculations.
The tool lets your agent filter results way down, letting you isolate specific payment types or restrict results based on exact dates. Need to see only the special dividends paid out in Q4? Or maybe you want to check payouts strictly from quarterly cycles versus annual ones? You just tell it what you're looking for, and it narrows the focus immediately.
Because the data is so granular, your AI client can track dividend consistency across different frequencies. It helps you see if a company sticks to its payment schedule—whether it's quarterly, or if they only pay once a year. This reveals crucial patterns in corporate commitment that simple charts miss.
It’ll pull together the necessary payout data so your agent calculates key metrics like dividend growth rates and historical yields. You don't need another spreadsheet program to calculate this; the raw data feeds the model, and you get the resulting financial insights back directly. This makes building precise financial models fast.
The server pulls full records of cash payouts for any supported ticker, giving you a massive dataset ready for your analysis. It handles the heavy lifting, gathering every single historical payment record—recurring, special, or supplemental—into one place. The tool allows filtering by ex-dividend date and lets you specify the desired payment frequency to keep your data tight.
When your agent processes this data, it compiles a massive history of payouts, giving you access to thousands of records per ticker. It’s built for serious deep dives into corporate finance, letting you model payout trends over decades without running into data caps or formatting headaches.
The capability to calculate historical yields and track dividend growth rates is what makes this server essential. You get the core payout figures needed to run those calculations yourself, meaning your research remains precise and auditable. It keeps the flow of information moving so you can focus on interpreting the numbers, not cleaning them up.
You'll use this to build sophisticated financial models that track how a company’s payouts have evolved through different economic cycles. You can cross-reference payment types—for instance, comparing consistent quarterly payments against larger, infrequent special distributions—to understand management's true commitment to shareholders. It gathers the full context of cash returns for every ticker it supports.
It processes massive amounts of financial data efficiently. When you set parameters like a specific date range and request payout frequency, the tool delivers only the relevant records. This means your AI client doesn't choke on irrelevant noise; it gets exactly what it needs—the raw, unfiltered historical dividend record for immediate use in your analysis.
019e38bd-cba8-73c5-afd3-cc04e1e6b172 How Massive MCP Works
- 1 Subscribe to Massive and input your API Key into your AI client.
- 2 Tell your agent you need a specific type of financial data (e.g., 'Show me the dividend history for AAPL').
- 3 The agent automatically invokes
list_dividends, sends the required ticker and date parameters, and returns structured payout records.
The bottom line is that you talk to your AI client like a human analyst, and it handles all the data retrieval via Massive.
Who Is Massive MCP For?
Financial analysts who spend hours manually compiling dividend payout sheets. Portfolio managers needing quick validation of portfolio timing. Quant developers building trading bots that need reliable historical financial feeds. If your job requires deep dives into corporate cash flows, this is for you.
Needs to quickly retrieve payout histories across multiple tickers to calculate yield changes and dividend growth rates.
Checks historical ex-dividend dates for major holdings to time portfolio rebalancing or sell points.
Integrates reliable financial distribution data into trading bots, eliminating the need for complex web scraping routines.
What Changes When You Connect
- Stop manual data compiling. You get clean, structured records for thousands of tickers using
list_dividends. No more cross-referencing multiple financial sites to build a single payout timeline. It just works. - Pinpoint specific payment types. Need to know how much was paid out as a special bonus vs. the regular quarterly dividend? You filter those exact distribution types with
list_dividendsin one query. - Model growth rates accurately. By pulling full historical data, you can feed clean records into your agent and calculate precise dividend growth rates—something messy spreadsheets often mess up.
- Manage portfolio timing better. Check the ex-dividend dates for all your holdings instantly. Your agent runs
list_dividendsto help you time sales or purchases against payout cycles. - Build reliable trading logic. Developers integrate this data into bots and research tools using the structured output from
list_dividends, skipping flaky web scraping entirely.
Real-World Use Cases
Calculating total historical yield for a new investment
An analyst is looking at Company X. Instead of downloading five years of annual reports, they prompt their agent: 'Run list_dividends for ticker XYZ and calculate the 5-year average dividend yield.' The agent executes the tool, gets all payouts, and returns a single, actionable percentage.
Checking if a special payout occurred in the past
A portfolio manager asks their agent to check for unique payments. They prompt: 'Use list_dividends on ticker ABC and filter specifically for any 'special' distributions after 2015.' The tool returns only those notable, non-recurring payouts.
Building a dividend tracking bot
A developer needs to feed historical data into a Python trading script. They call list_dividends with date range and ticker parameters. The agent sends back structured JSON records, perfect for immediate integration without cleanup.
Comparing payout frequency across two stocks
You want to compare KO (Coca-Cola) vs. PEP (Pepsi). You ask the agent to run list_dividends for both, filtering by 'quarterly'. The system compares the output structure and tells you which company has a more consistent payment schedule.
The Tradeoffs
Asking for future dividends
Prompting: 'What will my dividend be next quarter?' The tool only handles historical, finalized records. It can't predict the market.
→
To see what paid out last quarter, use list_dividends and specify the appropriate end date range to get verifiable history.
Using it for real-time pricing
Prompting: 'What is AAPL's stock price right now?' This server tracks payouts, not minute-by-minute market movement.
→
Use list_dividends to get payout records. If you need current trading data, check a dedicated real-time quote service.
Ignoring the ticker symbol
Prompting: 'Show me all dividend history.' The tool needs a specific stock to run against; it can't query everything at once.
→
Always include the required parameter: list_dividends requires a valid ticker (e.g., 'GOOGL').
When It Fits, When It Doesn't
Use this server if your primary job is financial forensics—specifically, analyzing how much cash was paid out over time and tracking payment patterns. If you need to calculate yield rates or track the difference between annual vs. quarterly payments, this tool is perfect.
Don't use it if: 1) You need real-time stock quotes (use a dedicated market feed). 2) You need fundamental company data like revenue projections (check SEC filings directly). 3) You are only interested in the current price movement. If your task revolves around past payouts and their consistency, then Massive's list_dividends is exactly what you need.
Common Questions About Massive MCP
Can I filter dividends by a specific date? +
Yes. You can use the ex_dividend_date parameter in the list_dividends tool to find distributions occurring on or after a specific YYYY-MM-DD date.
What types of dividend distributions can I identify? +
The list_dividends tool supports filtering by distribution_type, including 'recurring', 'special', 'supplemental', 'irregular', and 'unknown'.
How many dividend records can I retrieve at once? +
By default, the list_dividends tool returns 100 results, but you can increase the limit parameter up to a maximum of 5000 records per query.
How do I authenticate when using `list_dividends`? +
You must provide your Massive API key during server setup. Vinkius securely manages this credential, allowing your AI client to access the historical data without exposing raw keys.
What happens if I run `list_dividends` with an invalid stock ticker? +
The system returns a specific API error message. Your agent will relay this exact code, telling you precisely why the query failed and what input needs correction.
Does `list_dividends` require parameters other than the stock ticker? +
No, initially providing the ticker is enough to start. You can then refine results in subsequent prompts by specifying frequency or distribution type for deeper analysis.
What historical depth can I retrieve using `list_dividends`? +
The API provides comprehensive data spanning many years of a ticker's trading life. You can pull decades of payout history, limited only by the company’s record.
What format is the dividend data delivered in for analysis? +
Data arrives in a structured JSON format. This makes it simple to pipe directly into financial models or Python scripts without requiring complex parsing steps.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.