PluginBench
MCP Server
Active

Trading Signals MCP Server

io.github.roman-rr/trading-signals

Live AI crypto trading signals with entry, stop-loss, take-profit, and causal reasoning—no API key needed to start.

What is the Trading Signals MCP server?

The Trading Signals MCP server provides live cryptocurrency trading signals for AI agents like Claude and Cursor. It delivers bullish/bearish signals with full trade setup (entry, stop-loss, take-profit, leverage, position size) backed by 44 research-grounded algorithms and multi-expert consensus. Every signal includes a transmission chain showing the causal reasoning and is auto-verified against real prices.

Trading Signals monitors 50+ crypto perpetual markets across six dimensions (volume, positioning, price dynamics, cross-asset flows, microstructure, options) to identify trading opportunities. Three independent AI experts analyze each signal; only those with consensus fire. The service is free during beta, requires no API key for a 3-signal preview, and provides performance stats, paper-trading P&L, and confidence scores for each trade.

How to install Trading Signals

Copy-paste configuration for popular MCP clients.

transport: http
Config generated by PluginBench — verify against the source before use.
~/.cursor/mcp.json
{
  "mcpServers": {
    "trading-signals": {
      "url": "https://signals.x70.ai/mcp"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • get_signals — Retrieve active, verified, or all trading signals with entry, stop-loss, take-profit, leverage, and confidence scores.
  • get_signal — Fetch details for a single trading signal including transmission chain and causal reasoning.
  • get_signal_history — Access historical signal data to review past trades and performance.
  • get_stats — Retrieve performance statistics including hit rate, cumulative ROI, profit factor, and breakdowns by direction, coin, and model.

Use cases

  • Get real-time crypto trading signals with full trade setup and confidence scores for manual or automated trading.
  • Analyze signal performance metrics (hit rate, ROI, profit factor) to evaluate strategy effectiveness.
  • Build automated trading bots that fetch signals and execute trades on Hyperliquid or other exchanges.
  • Review transmission chains to understand the causal reasoning behind each signal.
  • Monitor verified signals against real prices to track which trades hit take-profit or stop-loss.

Trading Signals MCP server FAQ

What is the Trading Signals MCP server?

It provides live AI-generated crypto trading signals for agents like Claude and Cursor. Each signal includes entry price, stop-loss, take-profit, leverage, and position size, backed by 44 research-grounded algorithms and multi-expert consensus.

Is it free?

Yes, it is free during beta. No credit card required. You get 3 free signals without an API key; sign up at https://signals.x70.ai/mcp-signup for the full feed.

How do I install it in Cursor or Claude?

For Cursor, add the server to ~/.cursor/mcp.json with URL https://signals.x70.ai/mcp. For Claude Code, run `claude mcp add --transport http trading-signals https://signals.x70.ai/mcp`. For Claude app, use Customize → Connectors → Add custom connector with the same URL.

Do I need an API key?

No API key is required to try the service—you get a 3-signal preview. For the full feed, get a free key at https://signals.x70.ai/mcp-signup and pass it as a header (X-Api-Key) or query parameter.

What markets does it cover?

It monitors 50+ cryptocurrency perpetual markets, dynamically selected from top volume, funding, and open interest on Hyperliquid perps.

How accurate are the signals?

Each signal includes a confidence score (0-100) and is auto-verified against real prices. The server tracks hit rate, cumulative ROI, profit factor, and provides performance stats broken down by direction, coin, and model.

README (reference)

Source of truth, from the repository.

Trading Signals

⭐ Enjoying free signals? Push STAR to keep them free — it directly supports higher accuracy and continued development!

Trading Signals for AI Agents

17 triggers. 44 algorithms. 3 AI experts. Every signal backed by causal reasoning and verified against real prices.

Live crypto trading signals for Claude Code, OpenAI Codex, Cursor, Windsurf & 30+ AI agents. Every signal includes entry, SL, TP, leverage, position size, and a full transmission chain showing exactly which data points led to the trade.

FREE during beta. More stars = more development time = better signals for everyone.

Install

Claude Code Plugin (recommended)

/plugin install roman-rr/trading-skills

npx (Claude Code, Codex, Cursor, Windsurf, etc.)

npx skills add roman-rr/trading-skills

MCP Server (Claude, Cursor, Codex, VS Code)

Works without a key (3-signal preview). For the full feed, get a free key at https://signals.x70.ai/mcp-signup — the API Key page has copy-paste setup for every client.

Claude Code

claude mcp add --transport http trading-signals https://signals.x70.ai/mcp
# with a key:
claude mcp add --transport http trading-signals https://signals.x70.ai/mcp --header "X-Api-Key: YOUR_KEY"

Claude app (Desktop & claude.ai) — Customize → Connectors → Add custom connector, URL https://signals.x70.ai/mcp. Connectors have no header field, so with a key use https://signals.x70.ai/mcp?apiKey=YOUR_KEY.

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "trading-signals": {
      "url": "https://signals.x70.ai/mcp",
      "headers": { "X-Api-Key": "YOUR_KEY" }
    }
  }
}

Codex (~/.codex/config.toml, key in env var SIGNALS_API_KEY)

[mcp_servers.trading-signals]
url = "https://signals.x70.ai/mcp"
bearer_token_env_var = "SIGNALS_API_KEY"

Tools: get_signals, get_signal, get_signal_history, get_stats (register is deprecated — keys come from the dashboard).

OpenAI Codex CLI

See agents/openai.yaml for agent configuration.

Manual

# Claude Code
git clone https://github.com/roman-rr/trading-skills.git
cp -r trading-skills/trading-signals ~/.claude/skills/trading-signals

# OpenAI Codex CLI
cp -r trading-skills/trading-signals ~/.codex/skills/trading-signals

Always Watching

17 Triggers. 6 Groups. Every Minute.

The sentinel continuously scans 50+ perpetual markets for anomalies across six orthogonal dimensions -- volume, positioning, price dynamics, cross-asset flows, microstructure, and options-derived signals. A signal fires only when multiple independent dimensions agree, filtering noise from genuine opportunities.

Multi-Expert Consensus

Three specialized AI experts analyze every opportunity independently -- each with a different lens on market structure. Signals require agreement; conflicting views are flagged or filtered. The system continuously learns which analytical approaches perform best per market condition.

Research-Grounded

44 Scientific Methods. 53 Academic Citations.

Every algorithm is grounded in peer-reviewed research from quantitative finance, statistics, and machine learning -- spanning position sizing, anomaly detection, technical analysis, market microstructure, and adaptive risk management.

What You Get

FeatureDescription
Live signalsBullish/bearish with full trade setup -- entry, SL, TP, leverage, position size
Transmission chains2-4 causal reasoning steps per signal with specific data points
50+ coinsDynamically selected from top volume, funding, and OI on Hyperliquid perps
Confidence score0-100 AI conviction level per signal
Auto-verificationEvery signal tracked against real prices -- TP/SL monitoring every minute
Paper trading P&LReal trades on a virtual account with optimal position sizing
Dynamic risk controlConfidence-based leverage caps, volatility-calibrated SL, automatic regime detection
Performance statsHit rate, cumulative ROI, profit factor, breakdown by direction/coin/model

Signal Preview

CoinDirConfEntrySLTPLevR/RType
BTCBull87%$68,450$67,200$71,8003x2.7momentum_shift
ETHBear82%$3,840$3,920$3,6802x2.0funding_anomaly
SOLBull79%$142.50$138.00$152.002x2.1volume_spike

API Endpoints

MethodPathAuthDescription
POST/api/skill/registerNoDeprecated — returns signup_required; get keys at /mcp-signup
GET/api/skill/signalsAPI keyList signals (active/verified/all)
GET/api/skill/signals/:idAPI keySingle signal detail
GET/api/skill/statsAPI keyPerformance statistics

Example Prompts

Once installed, ask your AI agent:

  • "Get me the latest crypto trading signals"
  • "Show me today's highest-confidence BTC and ETH signals"
  • "What's the 30-day hit rate for these trading signals?"
  • "Build me a Python script that fetches crypto signals and alerts me on Telegram"
  • "Show me verified signals from the last week -- what hit TP?"

Pricing

FREE during beta -- no charges, no credit card.

Contributing

Issues, feature requests, and PRs are welcome. Please open an issue first to discuss changes.

License

Proprietary -- Free API during beta. Paid license required for commercial redistribution. See LICENSE.txt.

Related MCP servers

MCMCP AEMPS — CIMA logo

MCP server for the Spanish AEMPS CIMA pharmaceutical registry (20,000+ authorised medicines).

1
Python
View repository →

AI fantasy sports & entertainment intelligence. 75 tools across 10 sports + TV/Awards.

View repository →

Buyer-side trust oracle + capped sessions for x402 agents: verified_route, receipts, 17 free tools.

2
Python
View repository →

Search verified-open US grants (federal, state, foundation). Read-only MCP for AI agents.

View repository →
FAFableCut logo

FableCut

Active

Browser video editor driven by AI agents via JSON timeline and MCP; zero npm dependencies.

611
JavaScript
MIT
View repository →

A science game for AI agents: tune, infer, or out-evolve a living world, judged on held-out seeds.

0
JavaScript
View repository →