Analytics

midasflow.ai

Provides financial market data including signals, symbol scoring, candles, orderbook, and order flow for trading analysis.

1 endpoint14 known toolsFirst detected July 18, 2026Last detected August 29, 2026

ENDPOINT 1

https://mcp.midasflow.ai/mcp

No auth detected

MCP server metadata

Name: MidasFlow Flow API
Version: 1.28.0

Capabilities

experimentalpromptsresourcestools

Server instructions

MidasFlow Flow API — crypto market DATA / analytics, NOT financial advice. Recommended workflow: (1) get_accuracy → realized first-TP win-rate per source family; (2) feed a bucket's win-rate + average win/loss into calc_ev → expected value; (3) get_signals for the live feed. account shows your tier and remaining daily quota — self-throttle by it. Win-rate frame = P(price hit TP1 before SL), NOT realized PnL after fees. The confidence field is `model_confidence` (raw model score, NOT P(win); `prob` is a deprecated alias).

Known tools 14

get_signals

Pull recent MidasFlow SignalEvent records (newest first).

Inferred read-only

score_symbol

CROWN data product: calibrated P(first TP1 before SL) band + coarse trade plan (TP ladder %, SL %, weights) for ONE symbol, FOLDED with a pre-trade feed-safety check (is the feed live/real-volume/fresh, no phantom ticks).

Potential side effects

get_candles

Recent OHLCV candle bars for a symbol at a chosen timeframe — the raw price/volume history other tools are derived from.

Inferred read-only

get_orderbook

Live order-book snapshot for a symbol — bid/ask walls, book imbalance, spread — FOLDED with support/resistance levels (classic TA fused with cross-exchange book walls + Fibonacci) so you see resting liquidity AND the level map in one call.

Inferred read-only

get_flow

Per-symbol order-flow microstructure, grouped by `kind`.

Inferred read-only

get_heatmap

Liquidation-heatmap matrix for a symbol — price levels where leveraged positions cluster and are likely force-liquidated (price-magnet zones / liquidity pools).

Inferred read-only

get_context

Contextual market reads, grouped by `kind`.

Inferred read-only

get_whales

Large-player / forced-flow intel, grouped by `kind`.

Inferred read-only

get_market

Whole-market reads, grouped by `kind`.

Inferred read-only

get_accuracy

Realized track-record (proof of edge, forward-only, Wilson-bounded), grouped by `kind`.

Inferred read-only

account

Your mf_ key's account view, grouped by `kind`.

Inferred read-only

backtest

LAB / RESEARCH tool — replay an arbitrary {symbol, entry, tp, sl} setup over MidasFlow's 1m candle history and get its historical P(TP1-before-SL) + EV, in the canonical first-touch TP1 frame (same frame as get_accuracy).

Inferred read-only

analyze

LAB / RESEARCH tool — the full MidasFlow AI-Analyst report for a symbol: a synthesized narrative fusing flow, derivatives, levels, regime and signal context into a human-readable read RIGHT NOW.

Inferred read-only

calc_ev

LAB tool — pure local expected-value calculator over a win-rate and average win/loss percentages.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.midasflow-flow-api]
url = "https://mcp.midasflow.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "midasflow-flow-api": {
      "type": "http",
      "url": "https://mcp.midasflow.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: midasflow-flow-api
Remote MCP URL: https://mcp.midasflow.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "midasflow-flow-api": {
      "url": "https://mcp.midasflow.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "midasflow-flow-api": {
      "type": "http",
      "url": "https://mcp.midasflow.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "midasflow-flow-api",
  "transport": "streamable-http",
  "url": "https://mcp.midasflow.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for midasflow.ai was fetched 2026-08-21T16:25:37.489Z and is being refreshed.

Trust status Trusted

midasflow.ai is assessed as Trusted: Domain has an established technology history spanning over a year.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.