About quantustik
quantustik provides measured S&P 500 market data for investors and AI agents, including filings, trades, earnings, and market indicators. This package is a thin stdio proxy for its hosted MCP endpoint, with no local data cache.
Key features
- 01Retrieve Fear & Greed and earnings dates
- 02Review SEC filings and language changes
- 03Track insider and institutional activity
- 04Query Congress trade disclosures
- 05Access market data through a hosted endpoint
Use cases
- 01Check earnings dates and market indicators
- 02Review recent company filings
- 03Research insider, institutional, or Congress trades
- 04Connect a stdio-only MCP client to Quantustik
MCP support
The hosted service exposes nine tools through a streamable-HTTP MCP endpoint. This package proxies that endpoint over stdio for clients that do not connect to remote servers directly.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://quantustik.com/mcpclaude mcp add --transport http quantustik https://quantustik.com/mcp{"mcpServers":{"quantustik":{"type":"http","url":"https://quantustik.com/mcp"}}}Open in Cursor{"servers":{"quantustik":{"type":"http","url":"https://quantustik.com/mcp"}}}Open in VS Code{"mcpServers":{"quantustik":{"type":"http","url":"https://quantustik.com/mcp"}}}{"mcpServers":{"quantustik":{"serverUrl":"https://quantustik.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://quantustik.com/mcpAuth requiredTools
8This tool takes no parameters.
Details
From the project READMEQuantustik MCP server — S&P 500 market data
Quantustik is a market data service for the S&P 500 — prices, fundamentals, SEC filings, insider and Congress trades, macro indicators and market conditions — for investors and AI agents, through a dashboard, a REST API and an MCP server.
The hosted MCP server at https://quantustik.com/mcp (streamable-HTTP) needs
no API key. It serves nine tools:
| Tool | What it returns |
|---|---|
get_fear_greed | CNN Fear & Greed index (0-100) |
get_earnings_calendar | Next and last earnings dates for a ticker |
get_insider_pulse | SEC Form 4 insider activity, per ticker or an S&P 500 screener |
get_filings_digest | SEC 8-K event digest, per ticker or a recent site-wide feed |
get_filing_language_diff | What changed in the prose between a ticker's two most recent 10-K or 10-Q filings |
get_institutional_activity | 13F institutional ownership changes and SC 13D/G activist filings |
get_congress_trades | STOCK Act disclosures from the House Clerk and Senate eFD |
list_capabilities | Discover all tools and resources |
get_started | Onboarding: per-tier quotas and how a free API key raises them |
Every value carries its source and as-of date. Quantustik publishes measured data only, with no predictions and no recommendations.
Educational research only — not financial advice. Nothing here is a recommendation to buy or sell any security.
Connect
Clients that support remote streamable-HTTP servers can point straight at
https://quantustik.com/mcp. Clients that only support local stdio servers
(Claude Desktop, Cursor, Windsurf and others) can use this package, described
below. Anonymous use is allowed under a per-IP hourly quota; a free key from
quantustik.com/developers raises it.
What this package is
A thin stdio proxy to Quantustik's hosted MCP server. It lets MCP clients
that only support local stdio servers (Claude Desktop, Cursor, Windsurf,
and others) reach the live, keyless, streamable-HTTP endpoint at
https://quantustik.com/mcp.
This package does not implement an MCP server itself, run any model
locally, or cache any data. It is a small wrapper around
mcp-remote pointed at our
hosted endpoint. Every tool call is forwarded live to quantustik.com and
answered from the same data and quota system as the hosted endpoint.
If your MCP client supports remote streamable-HTTP servers directly, you
don't need this package at all — just point it at https://quantustik.com/mcp.
This wrapper exists only for stdio-only clients.
The full tool catalog lives at quantustik.com/developers.
Usage
Claude Desktop / Cursor / Windsurf
Add to your MCP client config (e.g. claude_desktop_config.json):
{
"mcpServers": {
"quantustik": {
"command": "npx",
"args": ["-y", "@quantustik/mcp-server"]
}
}
}
Command line
npx -y @quantustik/mcp-server
This starts a local stdio MCP server that proxies to
https://quantustik.com/mcp. Anonymous use is allowed under a per-IP hourly
quota; no setup required.
Optional: raise your quota with an API key
Get a free key at quantustik.com/developers, then set it as an environment variable:
{
"mcpServers": {
"quantustik": {
"command": "npx",
"args": ["-y", "@quantustik/mcp-server"],
"env": {
"QUANTUSTIK_API_KEY": "your-key-here"
}
}
}
}
Environment variables
| Variable | Purpose | Default |
|---|---|---|
QUANTUSTIK_API_KEY | Sent as Authorization: Bearer <key> to raise the anonymous per-IP hourly quota. | none (anonymous) |
QUANTUSTIK_MCP_URL | Override the remote endpoint (mainly for local development against a non-production instance). | https://quantustik.com/mcp |
Any additional CLI arguments you pass are forwarded to the underlying
mcp-remote proxy (e.g. --debug).
How it works
npx @quantustik/mcp-server runs a small Node script
(bin/quantustik-mcp.js) that spawns
mcp-remote against
https://quantustik.com/mcp using the http-only transport (our endpoint
is streamable-HTTP, not SSE). mcp-remote speaks stdio to your MCP client
on one side and streamable-HTTP to our server on the other — this package
just pins the URL, transport, and optional auth header so you don't have to
remember them.
Source
Server implementation (Python, FastMCP): the hosted endpoint's source lives
in mcplafed/autoevolve
(app/mcp_server.py, server.json). This wrapper repo only contains the
thin npm client shown above.
Disclaimer
Market data returned by the Quantustik MCP server is for educational and research purposes only and does not constitute personalized financial advice. Always consult a qualified financial professional before making investment decisions.
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.