mcpbeat Sign in

Maddog MCP Server

answering

Maddog is answering right now. Last checked 11 min ago. It exposes 5 tools. Last commit 27 Aug 2026.

Price-action reads with measured accuracy: day-type odds, breakouts, public scoreboard

Uptime history 74 days of history · worst day 99%
74 days agonow
100.0%
Uptime 24h
91 of 91 checks
5
Tools
read from the server
556 ms
Response time
average over 24h
0
Stars
last commit 27 Aug 2026

What changed 20

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 28 August 2026. No other catalogue keeps this.

2 Nov a tool changed version10 times that day
2 Nov 2 tool descriptions were rewritten3 times that day list_domestic_futures, price_action_read
2 Nov a tool changed the parameters it asks for2 times that day price_action_read
1 Nov a tool changed the parameters it asks for2 times that day price_action_read
1 Nov a tool appeared list_domestic_futures
1 Nov a tool changed version
28 Aug a tool appeared close_curve
and 12 more, back to 28 August 2026

Nothing serious here today

Today is the operative word: we check Maddog every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.

run in your terminal
claude mcp add mcp --transport http https://api.maddog.finance/mcp
Settings → Connectors → Add custom connector, then paste this address
https://api.maddog.finance/mcp
~/.codex/config.toml
[mcp_servers.mcp]
url = "https://api.maddog.finance/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://api.maddog.finance/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://api.maddog.finance/mcp"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

close
close_curve
The full probability curve of where today's US regular session closes: for any set of price levels, the probability that the session close prints above each one. Distances are measured in units of today's own volatility (ATR of the first 90 minutes) against 1,906 historical sessions grouped by day type. Validated against real-money prediction-market prices: on tail levels (>=0.5% from spot) this curve's log-loss beat Polymarket's own 'SPY closes above $K' ladder quotes in two independent windows; near the money the market was MORE accurate — use this for shape and tails, not direction. Available from 90 minutes into the day session. Same key and quota as price_action_read. Historical frequencies, not forecasts.
domestic
list_domestic_futures
Discover all supported mainland futures products, Chinese names, main-contract aliases, active delivery contracts, trading sessions and last data-check status. Free, no key, no credits. Search by Chinese name or product code before claiming a domestic future is unsupported. Covers SHFE, INE, DCE, CZCE, CFFEX and GFEX.
price
price_action_read
Read one instrument's current session the way a price action trader would, with measured statistics instead of opinions: a five-class day-type probability distribution (66% top-1 accuracy over a complete US day session against a 37% baseline, published confidence grades from 95% to 41% by grade), the window's first range breakout with its calibrated failure estimate (AUC 0.646 on held-out NQ), and — 90 minutes into the session — the measured odds that a new session high or low still prints before the close. Works on US stocks and ETFs, futures (ES=F), FX, crypto, Hong Kong and China A-shares. Anonymous callers get one first-look response per UTC day; after that, pass an API key in the X-API-Key header (get a free one with the request_free_key tool). Mainland futures directly reuse unchanged original daytype_v4 Transformer weights, features and temperatures, without domestic retraining or recalibration. Return five probabilities for any product with sufficient native inputs; before 90 trading minutes mark provisional. Never apply US accuracy or event-success probabilities. Domestic reads without model output are free. Historical frequencies, not trading recommendations.
request
request_free_key
Request a free evaluation key (qd_...): no card, no account — the key is emailed to the address given, never returned in this response. It unlocks 10 successful calls per UTC day. Ask the human for their email address first and send marketing_opt_in=true only with their explicit consent. Full access is $99.90/month with a 3-day free trial, checkout link comes back in any quota-exhausted error.
scoreboard
get_scoreboard
The standing public record of this service's own calls — free, no key. Every US trading day at 11:00 ET the day-session read for ES=F, NQ=F and QQQ is snapshotted verbatim; after the close each row is scored on whether a new session high or low actually printed after the read. Ties score against the model, days with no live read stay visible as gaps, and no row is ever edited. Recording began 2026-08-25. Use this to verify the claims before trusting any read.

Endpoints

URLTransportStateLatencyChecked
https://api.maddog.finance/mcp streamable-http answering 522 ms 11 min ago

Alternatives to Maddog

same job, measured the same way
AstraNL
by astranl

Dutch construction facts with measured accuracy + NL coordination. Never holds third-party funds.

36 tools answering
Public
by colaunched

Business ideas from real public demand, scored with dated evidence. No account needed.

4 tools answering
Marketintell
by marketintell

AI analyst desk for stocks, options & crypto with sourced trade setups and a public accuracy record.

17 tools answering
MoveSurge
by movesurge

Market news with the measured price reaction attached to the event that caused it.

13 tools answering
CellType UDI
by celltype

Search public biomedical datasets, measured results, papers, trials and drug evidence with sources.

answering
GATE Daily
by gatedaily

Ten original GATE CS practice questions a day, scored the GATE way, with worked solutions.

answering
Kalshi
by pipeworx-io

Kalshi MCP — US-regulated prediction-market data (no auth on public reads).

336 installs/wk 63 tools answering
Betsbeats
by betsbeats

Verify sealed BetsBeats picks, read the public record, and do odds math. Read-only. 21+.

6 tools answering

Maddog — questions

Answers built from our own checks of this server.

What can Maddog do?
It exposes 5 tools, read directly from the server on our last check. Among them: close_curve, get_scoreboard, list_domestic_futures, price_action_read, request_free_key. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Maddog working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 556 ms. The bar chart above shows every period we have measured.
How do I connect Maddog?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Maddog need an API key?
No. Maddog completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Maddog?
It answers our handshake in 556 ms on average, which is faster than 20% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Maddog open source?
We cannot say either way: 0 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.