AI Trading Signals

Get Live Trading Signals

get_signals

Read-only

List live crypto trading signals that are still open — coin, direction, confidence and the reasoning behind each. Use it to find current trade ideas; use get_signal for one signal by ID (live or resolved), get_signal_history for signals that already closed, and get_stats for aggregate hit rate. No key: a 3-signal preview. Free key: up to 100 signals, with entry, stop-loss, take-profit and leverage null (the response's announcement.upgradeUrl explains Pro). Pro: all levels. Returns { signals[], returned, totalMatching, filtersApplied, plan }, sorted by live PnL (best first). Optional filters narrow the list: direction, coins, confidence band, risk/reward, stop distance, open interest, 24h volume, tags, the anomaly that triggered it, days/hours to skip, a BTC 24h-return gate. Rate limits: 30 calls/hour per IP without a key, 300/hour on a free key.

Input Schema

TableJSON Schema

Name	Required	Description
`coin`	No	Single coin symbol (e.g. BTC). Case-insensitive. Convenience alias for coinInclude=<coin>.
`days`	No	Lookback window in days (1–30, default 7). Without a key or on the free plan only the last 24 hours are searched.
`limit`	No	Max signals to return (default 10, max 100)
`apiKey`	No	Optional. Your Signals API key. Omit it for a 3-signal anonymous preview; get a free key at https://signals.x70.ai/mcp-signup for full metadata.
`skipDOW`	No	Comma-separated day names to skip (e.g. "Saturday,Sunday"). Mondays toxic, weekends weak.
`coinOiMax`	No	Maximum open interest in USD. R13 uses $500k-$10M.
`coinOiMin`	No	Minimum open interest in USD (e.g. 500000 for $500k). OI <$500k coins historically toxic.
`direction`	No	Filter by signal direction. "bullish" = long. Default = any.
`coinVolMin`	No	Minimum 24h notional volume in USD.
`coinExclude`	No	Comma-separated coin blocklist. Hyper-blacklist used by Lean v2-R: "kPEPE,ADA,HYPER,LDO,LINEA,2Z".
`coinInclude`	No	Comma-separated coin allowlist (e.g. "BTC,ETH,SOL").
`skipHourUtc`	No	Comma-separated hours UTC to skip (0..23). EU/US overlap 9-13 weakest.
`tagsInclude`	No	Comma-separated tags (any-of match).
`btcRet24hMax`	No	Skip if BTC 24h return % > this (e.g. 1.5). H1 regime gate: BTC rally rotates flow away from alts.
`btcRet24hMin`	No	Skip if BTC 24h return % < this.
`slDistPctMax`	No	Maximum stop-loss distance in %.
`slDistPctMin`	No	Minimum stop-loss distance in % (e.g. 3 = ≥3% to SL). SL≥3 drops the toxic [2,3) bucket.
`confidenceMax`	No	Maximum confidence (0..1). Best band 0.62-0.76.
`confidenceMin`	No	Minimum confidence (0..1). Counter-intuitive: >0.76 historically underperforms.
`primaryTrigger`	No	Sentinel anomaly trigger name (e.g. "vpin_toxicity" for the S9 Vpin Sniper preset).
`riskRewardRatioMax`	No	Maximum risk/reward ratio. Champion v1 uses RR<1.5.
`riskRewardRatioMin`	No	Minimum risk/reward ratio.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 8, 2026

changedInput schema / properties / days / description

Previous value: -"Lookback window in days"New value: +"Lookback window in days (1–30, default 7). Without a key or on the free plan only the last 24 hours are searched."

First observedSep 14, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only cover the safety profile (readOnly/openWorld/non-destructive); the description adds substantial behavior the agent cannot get from them: tiered plan gating (3-signal anon preview, 100 on free with nulled entry/SL/TP/leverage, full on Pro), per-IP rate limits (30/hr vs 300/hr), and sort order by live PnL.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded and dense but organized in a clear progression: purpose, alternatives, plan tiers, return shape, filters, rate limits. Long, yet essentially every clause carries distinct information; a minor trim would not hurt.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, but the description discloses the return envelope ({signals[], returned, totalMatching, filtersApplied, plan}), sort order, and the upgrade path in the response. Plan gating and rate limits complete what an agent needs before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description lists filter categories (direction, coins, confidence band, risk/reward, stop distance, OI, volume, tags, trigger, day/hour skips, BTC gate) but adds no syntax or semantics beyond what the schema already documents in detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (live, still-open crypto trading signals) and explicitly distinguishes itself from three siblings by name. An agent can tell this apart from get_signal and get_signal_history without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use ('find current trade ideas') plus named alternatives with their distinct conditions: get_signal for one by ID, get_signal_history for closed signals, get_stats for aggregate hit rate. Nothing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All AI Trading Signals tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?