Kaleidoscope MCP for quant research

Leak-safe by construction

Point-in-time filings, survivorship-complete base rates, and event signals you can query "as of" any date. Prototype hypotheses in your AI client; ship on the API.

Point-in-time, leak-safe Failures in the denominator MCP for research, API for production

One protocol — bring it to the assistant you already use

Claude ChatGPT Gemini Cursor + any MCP client
Before / after

How the work changes

The same jobs, without the exports, the tabs, or the unverifiable answer.

Before
Point-in-time reconstruction meant building your own filing-date joins and hoping nothing leaked.

With MCP
Every tool accepts an as-of date and returns what was knowable then — leak-safe by construction, not by discipline.

Before
Base rates computed on surviving tickers — inflated by everything that quietly disappeared.

With MCP
Survivorship-complete populations, with delistings, failures, and discontinued programs in the denominator.

Before
Testing a feature idea took a week of scraping and parsing before the first read.

With MCP
Probe 529 event classifiers and 152M classified filing sentences in plain English, in an afternoon.

The prompt pack

Ask in plain English

Run these today in Claude, ChatGPT, or any MCP client — each returns a cited answer.

You ask

Reconstruct BridgeBio's pipeline as it was knowable at the end of 2020.

You ask

Which companies filed Item 4.02 non-reliance 8-Ks last quarter?

You ask

What fraction of programs targeting TTR have historically succeeded?

You ask

Rank my watchlist by consecutive quarters of net institutional inflow.

Browse the full prompt library
Your data layers

The servers this desk runs on

Connect any subset — each is a focused, cited surface for its own domain.

Research vs production

MCP for research, API for production

Explore hypotheses in Claude against the same point-in-time corpora your production code would use — then ship on the Kaleidoscope API platform. Same data, same provenance contract, production delivery.

Explore the Kaleidoscope platform
Straight answers

The questions this desk asks first

Is chat the only interface?

No — MCP is the research channel: the fastest way to explore the data and pressure-test ideas. For production pipelines, the same corpora are available through the Kaleidoscope API platform. Ask about delivery options during your demo.

What history depth do I get?

Quarterly XBRL fundamentals back to ~2009 for ~4,400 companies; 13F position history 26+ quarters; classified filing sentences 2022–2026; news 2020–2026. Each tool states its own coverage window — no silent extrapolation.

How is point-in-time enforced?

Answers are reconstructed from what was filed and public on the as-of date. If a fact was not knowable then, it is not in the answer — the same contract that makes backtests honest.

How fresh is the data?

13F refreshes every ~4 hours from EDGAR, news daily, and filings flow through as the SEC publishes them.

Read-only tools, no side effects, and your queries are never used to train models. How we handle data

See it on your own questions

Request a demo and we'll walk through the workflow above with your names, your dates, and your questions.

Request a Demo