Article-level events with a 9-class taxonomy, a materiality score, and 3- and 5-day price-move correlation — deduped to one row per story, and cited.
One protocol — bring it to the assistant you already use
One question. Your AI composes the tools and returns a cited answer.
What news moved TSLA the most over the past year?
Show M&A-related news across semiconductors last quarter.
Which press releases had the biggest 3-day price move this month?
Summarize regulatory news for this ticker, cited.
Rank the news that actually moved a stock — by 3- and 5-day price-move correlation, not recency.
M&A, legal, regulatory, personnel, capital action, and more — every article classified.
How material was this story? A score per article, so noise sinks and signal rises.
One row per story, not per wire copy — promotional content filtered out.
Pair the news with the filing signals behind it, each cited.
The same trust contract every server in the family follows.
What was actually knowable on a date — no hindsight. Real backtests, not leakage.
The failures are in the denominator, not just the winners the model remembers.
Every number carries its filing and snippet. NULL means unknown, never invented.
SEC filings, 13F, N-PORT, ADV, and funding rounds — live, past any training cutoff.
Rank catalysts by market impact and catch the story that's moving the stock.
See which releases land — materiality and price reaction, not pickup counts.
Structured, deduped news events your models can consume via tool calls.
Paste the endpoint into your client's connector settings. Sign in with your allowlisted email — access is by invitation.
https://mcp-news.kscope.io/mcp/
Works with Claude (desktop & web), Claude Code, Cursor, and any MCP client over HTTP. On first use your client opens a sign-in tab — enter your email for a one-time link.
Request a demo and we'll show you cited, point-in-time news & press answers in your own AI client.
Request a Demo