Hey, it's Cindy 🌱 You commented trades, so here is the current Unusual Whales MCP setup, plus prompts that separate disclosure data from an investment signal.
btw the waitlist for AI System Club is now open! If you're keen on using AI to automate your content, video editing, job search, business or build AI agents, feel free to sign up (only if you want to hehe). Ps. the waitlist gets first dibs:)
the outcome
What you get
A connected congressional-trading data source, a weekly disclosure digest, and a cross-reference workflow that labels every date, delay, and source.
Use the guide in order. Gather the real inputs, run the prompts against those inputs, inspect the evidence, then make one reviewable change at a time.
start here
Set it up step by step
Get an Unusual Whales API key from its API dashboard. Keep it in an environment variable, never inside a prompt, screenshot, or committed file.
Connect the official hosted MCP endpoint to Claude Code using the command below, then restart or run /mcp as needed.
Ask for congressional transaction disclosures from a defined date range. Preserve transaction date and disclosure date as separate fields.
Cross-reference disclosed names with current price data and institutional 13F filings, while stating that 13F filings are also delayed snapshots.
Use the output to form research questions. Do not infer insider knowledge or buy solely because a politician disclosed a transaction.
Using the connected Unusual Whales tools, pull congressional stock transaction disclosures published in the last seven days. Return member, chamber, ticker, asset name, transaction type, reported value range, transaction date, disclosure date, and days of reporting delay. Rank by the midpoint of the disclosed value range, but label that midpoint as an estimate. Then cross-reference each ticker against the most recent available institutional 13F filings and current price data. Keep every source and as-of date beside the figure. Separate facts from inference, flag missing data, and finish with research questions only, not buy or sell recommendations.
check the work
Quality gate before you trust it
1 The MCP endpoint is https://api.unusualwhales.com/api/mcp and the API key is supplied through the header or environment.
2 Transaction date and disclosure date appear in separate columns.
3 Value is shown as the statutory reported range; any midpoint is clearly labelled an estimate.
4 Current prices and 13F data carry their own as-of dates.
5 The report says disclosures may be delayed and does not present overlap as proof of an edge.
6 Save the source links, as-of date, and final evidence beside the output so another person can reproduce the check.
Guardrail. This is educational market research, not investment advice. Congressional disclosures can be delayed, contain broad value ranges, and omit economic context. Never frame timing as proof of wrongdoing or treat a disclosed trade as a recommendation.
keep it useful
Save the evidence with the workflow
Save the prompt with the source links and the date you verified them. When the tool, policy, price, interface, or documentation changes, update the guide before you reuse the workflow. Keep the inputs and outputs beside the project so the next run can be checked instead of reconstructed from memory.
the waitlist is now open
AI System Club is launching soon
Build AI systems with me through recorded lessons you can follow at your own pace. Join the waitlist for first access and the founding price.
btw this list gets first dibs the moment doors open :)