Trading Signals logo

Trading Signals

Live crypto trading signals with reasoning, verification, performance statistics, and optional trade levels.

Install Trading Signals

Pick your client, then add it in one click or paste the config.

Streamable HTTP (Remote)
Server URL
https://signals.x70.ai/mcp/connect

Remote servers are added in the app, not the config file: Customize → Connectors → Add custom connector, then paste this URL.

Overview

Trading Signals MCP server provides live crypto market signals for AI agents, including direction, confidence, causal reasoning, and verification against real prices. Its MCP tools list open signals, inspect individual outcomes, review resolved history, and calculate aggregate performance. Connect through the hosted HTTP endpoint with browser sign-in, an API key, or a three-signal public preview. Reach for it when an agent needs current crypto ideas or historical performance data rather than direct exchange order execution.

Use cases

  • Fetch current crypto trading signals
  • Filter signals by coin and confidence
  • Review resolved signals and verification outcomes
  • Check recent hit rates before acting
  • Build alerts from signal updates

Key features

  • Live open-signal feed
  • Causal reasoning and market data
  • Signal verification against real prices
  • Historical signal review
  • Aggregate hit-rate and ROI statistics
  • Optional entry, stop-loss, take-profit, and leverage data

Tools5

What Trading Signals lets your agent do. Expand a tool for its parameters.

Verified live~2.1k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

16/16 checks healthy over the last 45d

What it can do

From the 5 tools this server returned when we ran it.

Handles credentials · 4Read-only tools · 5

Observed 2026-10-16 in an isolated sandbox. A description of reach, not a security audit.

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars127Stargazers on the source repository.
Last commit3d agoMost recent push to the default branch.
Tools exposed5Callable tools this server registers over MCP.

How Trading Signals works

What Trading Signals does

Trading Signals exposes live crypto trading analysis through MCP. Open signals include the coin, bullish or bearish direction, confidence score, reasoning chain, and supporting market data. Signals are tracked against real prices so agents can inspect whether take-profit or stop-loss conditions were reached and whether verification succeeded or failed.

The underlying system watches more than 50 perpetual markets and evaluates anomalies across volume, positioning, price behavior, cross-asset flows, market microstructure, and options-derived data. Three specialized AI analyses are used for each opportunity, and signals require agreement between views or are flagged when the views conflict.

How it works

Use the hosted MCP endpoint rather than running a local trading service. The browser-based connection URL lets an MCP client start sign-in and account authorization. A separate endpoint supports API-key authentication for clients and scripts that cannot complete browser sign-in.

Without authentication, the service returns a preview of three live signals and public performance statistics. A free key provides the broader live feed and limited history. Pro access adds trade levels such as entry, stop-loss, take-profit, leverage, and position size.

Signals are returned with optional filters for direction, selected coins, confidence, risk/reward, stop distance, open interest, volume, tags, anomaly type, time exclusions, and a BTC 24-hour return condition. Results are sorted by live profit and loss, with account-plan information included in the response.

Setup and configuration

For Claude Code, add the hosted HTTP connection with:

Terminal
claude mcp add --transport http trading-signals https://signals.x70.ai/mcp/connect

The same connection URL can be added as a custom connector in the Claude app or configured in Cursor. For clients that use API keys, create a key at the Trading Signals signup page and send it as the X-Api-Key header. Codex can read the key from SIGNALS_API_KEY:

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

The repository also supports installation through the Claude Code plugin command, npx skills add roman-rr/trading-skills, or manual copying of the skill directory into the Claude Code or Codex skills folder.

Tools and capabilities

  • get_signals lists open signals and supports market, confidence, risk, liquidity, timing, and anomaly filters.
  • get_signal retrieves a live or resolved signal by ID, including price, PnL, reasoning, and verification status.
  • get_signal_history reviews resolved signals, with pagination through a cursor and plan-dependent history depth.
  • get_stats reports resolved-signal hit rates, counts, leverage averages, direction breakdowns, monthly figures, and—when authenticated—ROI metrics.
  • register is retained for older clients but is deprecated and does not create or store an API key.

Limitations and notes

The free unauthenticated preview is limited to three signals and has an IP rate limit of 30 calls per hour. Free keys allow up to 100 signals and 300 calls per hour; free-plan trade levels and history fields are returned as null or restricted. Pro history supports the configured days range up to 90 days.

Performance statistics describe resolved historical signals and are not predictions of future returns. The service supplies signals and analysis; the documented tools do not place exchange orders. Account-related announcements returned by the service should be shown to the user.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Trading Signals

Trading Signals is an MCP server that connects AI agents to live crypto trading signals from signals.x70.ai. Its main tools list open signals, retrieve signals by ID, review resolved history, and calculate aggregate performance statistics. Results include reasoning, confidence, direction, verification outcomes, and plan-dependent trade levels.

Install it by adding the hosted MCP URL to your client, using the Claude Code plugin, or running `npx skills add roman-rr/trading-skills`. Claude Code can connect with `claude mcp add --transport http`; Cursor and Claude support the hosted connection URL.

Yes, Trading Signals works with Cursor through its MCP configuration. Add `https://signals.x70.ai/mcp/connect` to `~/.cursor/mcp.json` for browser-based sign-in, or use the `/mcp` endpoint with an `X-Api-Key` header.

Yes, the public endpoint provides a three-signal preview and public statistics without a key. A free key expands access to the live feed and limited history, while Pro adds trade levels and deeper history.

Use `get_stats` for aggregate hit rates, verification counts, direction breakdowns, and available ROI figures, or use `get_signal_history` to inspect resolved signals individually. Historical results do not predict future returns.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewTrading Signals AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/trading-signals?style=directory)](https://allmcps.com/mcp/trading-signals)
HTML Embed
<a href="https://allmcps.com/mcp/trading-signals"><img src="https://allmcps.com/api/badge/trading-signals?style=directory" alt="Trading Signals on AllMCPs" /></a>