Skip to content
MCP server

PlainQuant

Free, read-only US and Hong Kong stock research: event studies, scores and SEC filings

Status and history

Answered our latest tool-list check 22 hours ago with 8 tools. It will be marked verified after 3 successful checks in 7 days.

Install
Pricing
Free
Platforms
API, Web
Runs
Remotely
Version
1.1.0
Listing updated
3 days ago

About PlainQuant

PlainQuant is a free MCP server for finance and payments. It runs as a hosted remote server, so there is nothing to install locally.

PlainQuant answers questions about what markets did after past events. Its event_study tool shows the US market two weeks, four weeks and three months after Fed decisions, CPI or jobs reports, elections and market drops, or for one stock if you give a symbol. index_move_study does the same after an index move such as the Nasdaq falling 10% in two days.

Other tools give trend and business scores for US and Hong Kong stocks along with whether those scores have predicted anything, upcoming Fed, CPI and jobs dates, plain backtests of library stock-picking rules beside an honest estimate, a market snapshot of trend bands and strongest and weakest groups, and a company's important SEC filings.

It needs no account or key and none of the tools uses AI. Limits are 60 requests a minute per IP across the API and MCP, and figures are fractions that describe the past, not the future.

Install

Run in a terminal

claude mcp add --transport http plainquant https://plainquant.com/mcp

Add to Settings → Connectors → Add custom connector

https://plainquant.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "plainquant": {
      "url": "https://plainquant.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "plainquant": {
      "type": "http",
      "url": "https://plainquant.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "plainquant": {
      "serverUrl": "https://plainquant.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "plainquant": {
      "type": "http",
      "url": "https://plainquant.com/mcp"
    }
  }
}

Tools this server provides (8)

Read directly from the server.

list_events
The events PlainQuant has history for (Fed decisions, CPI, jobs reports, US elections, quarterly options expiry, market drops), with ids, names in English and Chinese, and aliases.
event_study
For each past occurrence of the event, the move of the market (market: US = the S&P 500 via SPY, the default for US events; HK = the Hang Seng Index, from its first close after the news; 'measured' in the answer names it) 2 weeks, 4 weeks and 3 months later (fractions: 0.037 = +3.7%), plus median, share up, worst and best beside any window of the same length. With too few occurrences only the list
index_move_study
Like event_study, for a move of an index found in our prices: index SPY (S&P 500), QQQ (Nasdaq-100) or HSI (Hang Seng Index) moving pct percent (signed: -10 = a fall of 10% or more) within days trading days (a fall without days = from its high). Use for 'what happens if the Nasdaq drops 10% in two days' or 'what does Hong Kong do after the S&P 500 falls 3% in a day' (market HK).
check_stocks
Trend and business scores (1-100) for up to 20 US or Hong Kong stocks, the industry ranks behind them, whether each is stretched above its average, and whether the scores have predicted later returns. Accepts tickers (NVDA), HK codes (700) or company names, comma-separated.
upcoming_events
Fed decisions, CPI and jobs reports scheduled in the next days (default 30, at most 180), copied from each official calendar, each with the link to what the market did after past ones. Use for 'what market events are coming this week'.
rule_estimates
For each of PlainQuant's library stock-picking rules (US and Hong Kong) at default settings: the plain backtest's return a year after trading costs beside the honest estimate left after delisted stocks and untuned test periods (fractions: 0.05 = 5% a year), the trade count and the test window. Use for 'does momentum / value / moving-average investing work' or 'how much do backtests overstate'.
market_snapshot
US and Hong Kong large stocks as of each market's last close (the date is as_of): how many have a strong, good, mixed or weak price trend, how many are stretched above their average, and the strongest and weakest groups by median trend. A description of that day, not a forecast. Use for 'how broad is the rally' or 'which sectors are strongest'.
company_filings
A US stock's important SEC filings in the last days (default 30, at most 90): results, 10-Q and 10-K, officer or director changes, major agreements and deals, 5%+ stakes (13D), with links to the filings on SEC EDGAR. Takes a ticker or company name. Hong Kong is not covered.

What it does

Event studies
Shows market moves after past Fed decisions, CPI and jobs reports, elections and drops.
Index move study
Looks at what followed an index fall or rise of a given size.
Stock scores
Gives trend and business scores for US and Hong Kong stocks and tests whether they predicted anything.
Rule backtests
Pairs each library rule's plain backtest with an honest estimate.
SEC filings
Lists a US company's important filings.
No key needed
Free and read-only, with the same data available as a JSON API.

Good for

  • See what stocks did after past Fed decisions
  • Test a drop scenario like a 10% Nasdaq fall
  • Check scores for US and Hong Kong tickers
  • Find upcoming Fed, CPI and jobs dates
  • Pull recent SEC filings for a company

Pricing

Free

Free, no account or key

Prices change. Check plainquant.com before you buy.

PlainQuant FAQ

Does it need an account or API key?

No. It is free, read-only and needs neither.

Does it use AI to produce figures?

No. The page says none of the tools uses AI.

What is the rate limit?

Up to 60 requests a minute per IP across the API and MCP.

Do the figures predict the future?

No. They describe the past, not the future.

Is PlainQuant free?

Yes. PlainQuant is free to use.

How do I add PlainQuant to Claude Code?

Run this command in your terminal: claude mcp add --transport http plainquant https://plainquant.com/mcp

What are the best alternatives to PlainQuant?

The closest alternatives to PlainQuant are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Solana MCP by Vybe, Tapetide - Indian Stock Market MCP and World Monitor.

Alternatives to PlainQuant

  1. Open-source analytics app where an AI agent builds charts and dashboards from your data

    • Remote
    • Open source
    • 7.7K GitHub stars
    • Analytics and data
  2. Hosted MCP connector for managing Google Ads, Meta Ads, GA4 and Search Console from chat

    • 8 tools
    • Remote
    • Freemium
    • 8.1K GitHub stars
    • Marketing and SEO
  3. Remote MCP server exposing the Vybe Solana API to AI clients and code editors

    • 44 tools
    • Remote
    • 2.8K GitHub stars
    • Finance and payments
  4. Indian NSE and BSE stock market data for AI assistants through 48 MCP tools

    • 17 tools
    • Remote
    • Freemium
    • 150 GitHub stars
    • Finance and payments
  5. World Monitor

    MCP server

    Live geopolitical intelligence dashboard with an API and MCP server for agents

    • Remote
    • Freemium
    • Analytics and data
  6. Budget Tracker

    MCP server

    Local MCP expense ledger that logs receipts and mileage, splits VAT and prepares rebilling

    • 14 tools
    • Remote
    • Freemium
    • 2 GitHub stars
    • Finance and payments