The Kaleidoscope MCP family

One protocol. Every corner of the market.

A growing family of Model Context Protocol servers — each a cited, point-in-time data layer for a different domain. Connect the ones you need to Claude, ChatGPT, Gemini, or any MCP client.

10 live servers · connect any subset Cited & point-in-time Read-only, auto-approvable

One protocol — bring any of them to the assistant you already use

Claude ChatGPT Gemini Cursor + any MCP client
How it works

From your question to a cited answer

The Model Context Protocol lets your AI call these servers directly — no copy-paste, no exports.

You ask

In plain English, inside your AI client.

Your AI composes tools

Claude, ChatGPT, or any MCP client picks the right calls.

Kaleidoscope MCP

Reads primary sources — SEC & SEDAR filings, 13F, funding, and more.

A cited answer

Point-in-time and traced to the filing it came from.

Every step is read-only and auto-approvable — nothing invented, nothing mutated. See how to connect

The family

Pick your data layer

Each MCP is a focused, cited data layer for one domain — on its own subdomain, ready to plug into your AI client.

SEC · 13F · ADV · Fundamentals

SEC

Cited SEC filings, 13F institutional flow, activist campaigns, adviser (ADV) data, and XBRL fundamentals — point-in-time.

Live · mcp
Canadian mining · NI 43-101

SEDAR

Canadian mining research from filed technical reports — NPV, IRR, tonnages and grades, extracted from NI 43-101 filings on SEDAR and verified against the source.

Live · mcp-sedar
Private-company funding

Funding

Private-company funding — rounds, investors, and valuations — with SEC context where private companies cross over.

Live · mcp-funding
Material agreements

Agreements

A self-contained corpus of material contracts and legal agreements — searchable, comparable, and cited to the clause.

Live · mcp-agreements
M&A deals

Mergers

Announced and closed transactions, acquirers, terms, and comparables — with SEC context on every deal.

Live · mcp-mergers
Biotech pipelines

Bio

Point-in-time drug pipelines, survivorship-complete base rates, program trajectories, and target landscapes — cited to the 10-K.

Live · mcp-bio
News & press

News

Article-level events with a 9-class taxonomy, a materiality score, and 3/5-day price-move correlation — deduped and cited.

Live · mcp-news
Catalysts & macro

Catalyst

Earnings, scheduled events, and macro releases that move markets — dated, cited, and point-in-time.

Live · mcp-catalyst
Power sector

Power

Generation, capacity, and the data behind the AI power-demand trade — cited and point-in-time.

Live · mcp-power
Corporate debt

Tranche

Issuer debt, bond cards, holders, and refinancing screens across the corporate-debt panel — cited to the filing.

Live · mcp-tranche
Built for your desk

Start from your workflow

Guides for how each desk uses the family — the workflow, the objections, and a prompt pack to run today.

Why it's different

Primary-source data an LLM can't fabricate

Every server returns the same trust contract — so the answer isn't just fast, it's defensible.

Point-in-time

What was actually knowable on a date — no hindsight. Real backtests, not leakage.

Survivorship-complete

The failures are in the denominator, not just the winners the model remembers.

Sourced, not guessed

Every number carries its filing and snippet. NULL means unknown, never invented.

Post-cutoff fresh

SEC filings, 13F, N-PORT, ADV, and funding rounds — live, past any training cutoff.

See why AI needs a cited data layer
By the numbers

Deep, fresh, and cited

152M
Classified SEC filing sentences
73M
13F institutional holdings rows
52K
Form ADV advisers profiled
~15 min
SEDAR filing freshness
Contradictions cut in half

We test this on a 50-question finance-analyst benchmark we run internally — questions that require citing specific filings, dates, and figures. Grounded in Kaleidoscope data, the model's self-contradictions drop by half, and it answers questions it previously couldn't answer at all (0 of 50 → 10 of 50). The lift comes entirely from the data — same model, same prompts.

Not sure which layer you need?

Request a demo and we'll map your workflow to the right MCP — or several — in your own AI client.

Request a Demo