NeuroTrade Signal API
Server Details
AI-powered crypto trading signals: direction, confidence, TP/SL, thesis, technicals. 8 strategies.
- Status
- Healthy
- Uptime
- 100.0% over 39 days
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
TDQS
Scored across 2 tools
The two tools serve completely different purposes: one generates trading signals, the other checks account quota. There is no ambiguity between them.
Both tools follow the verb_noun pattern: generate_signal and get_account. This is consistent and predictable.
With only 2 tools, the surface feels thin for a trading signal API, which typically might include backtesting or historical data. However, the tools are directly relevant to the core purpose.
The set covers signal generation and quota management, but lacks obvious supporting operations like fetching historical signals or managing signal subscriptions. This leaves some gaps for an agent needing broader trading workflow coverage.
Available Tools
2 toolsgenerate_signalAInspect
Generate an AI-powered crypto trading signal for a given pair and timeframe. Returns: action (OPEN_LONG | OPEN_SHORT | CLOSE), confidence (0.0–1.0), entry_price, take_profit (array of price levels), stop_loss, risk_reward ratio, indicators (rsi, macd, ema_20, atr), risk_flags (overbought_rsi | oversold_rsi | low_volume | high_spread | near_resistance | near_support), generated_at (ISO 8601), expires_at (ISO 8601), and quota_remaining. The thesis field contains LLM reasoning and is only present when include_thesis=true. On quota exhaustion returns error_code=QUOTA_EXCEEDED with Retry-After header. Requires Authorization: Bearer nt_.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Trading pair in BASE/QUOTE format, e.g. BTC/USDT, ETH/USDT, SOL/USDT. | |
| strategy | No | Signal strategy to apply. Defaults to trend_rider. | |
| timeframe | No | Candlestick timeframe for signal analysis. Defaults to 15m. | 15m |
| personality | No | Risk personality shaping confidence weighting and TP/SL aggressiveness. Defaults to scalper. | |
| include_thesis | No | When true, includes the LLM-generated reasoning in the `thesis` field of the response. Adds ~200ms latency. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully carries the behavioral transparency burden. It discloses authentication requirements (Authorization: Bearer nt_<api_key>), detailed return structure with enums and conditionals (thesis only when include_thesis=true), error behavior (QUOTA_EXCEEDED with Retry-After header), and response expiry. This is comprehensive and goes beyond typical descriptions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single dense paragraph that front-loads the purpose and then enumerates return fields, error handling, and auth. Every sentence earns its place, and there is no fluff. However, the length could be streamlined with bullets for readability, so it is not maximally concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description compensates thoroughly by listing all response fields, their types/enums, conditional fields, and edge cases (quota exhaustion). It also covers auth and response expiry, ensuring the agent understands the tool's full behavior despite no structured output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all five parameters are already documented in the input schema. The description adds minimal parameter-specific value beyond mentioning 'pair and timeframe' and the include_thesis conditional. This matches the baseline of 3 for high coverage, but does not elevate it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Generate an AI-powered crypto trading signal for a given pair and timeframe.' This clearly distinguishes it from the sibling tool get_account, which handles account information. The return fields reinforce the purpose without ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage via 'for a given pair and timeframe' but does not explicitly state when to use this tool versus alternatives or when not to use it. It lacks exclusions or references to sibling tools, so usage guidance is only inferred from the purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_accountAInspect
Return the current NeuroTrade B2B API quota status: plan tier, calls used, calls remaining, and quota reset date. Requires a valid NeuroTrade B2B API key.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosure. It notes that a valid API key is required, which is useful, but it does not mention whether the operation is read-only, whether it consumes quota, or any potential side effects. This is basic but not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that states the purpose and key requirement without extraneous words. It is highly concise and well structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters and no output schema, the description adequately lists the return fields and the necessary API key. It is complete for this simple tool, though it could optionally mention quota consumption behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so the baseline is 4. The description does not need to elaborate on parameter meaning, and the schema coverage is complete (100%).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a clear verb 'Return' and specifies the resource: 'current NeuroTrade B2B API quota status'. It enumerates the exact fields (plan tier, calls used, calls remaining, reset date) and is distinct from the sibling tool generate_signal.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for checking API quota but provides no explicit when-to-use guidance or comparison with alternatives. It mentions the API key requirement as a prerequisite but does not state situations where generate_signal would be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- Changed
generate_signal9 fields changed- changed
Input schema / properties / include_thesis / descriptionPrevious value: -"Include the AI narrative thesis in the response."New value: +"When true, includes the LLM-generated reasoning in the `thesis` field of the response. Adds ~200ms latency." - changed
Input schema / properties / personality / descriptionPrevious value: -"Signal personality shaping confidence weighting: scalper, swing, macro, trend_rider, news_reactive, breakout_hunter"New value: +"Risk personality shaping confidence weighting and TP/SL aggressiveness. Defaults to scalper." - added
Input schema / properties / personality / enumAdded value: +[ + "scalper", + "swing", + "macro", + "trend_rider", + "news_reactive", + "breakout_hunter" +] - changed
Input schema / properties / strategy / descriptionPrevious value: -"Strategy name: trend_rider, breakout_hunter, scalper, swing_master, macro_lens, news_reactive, momentum_surge, mean_reversion"New value: +"Signal strategy to apply. Defaults to trend_rider." - added
Input schema / properties / strategy / enumAdded value: +[ + "trend_rider", + "breakout_hunter", + "scalper", + "swing_master", + "macro_lens", + "news_reactive", + "momentum_surge", + "mean_reversion" +] - changed
Input schema / properties / symbol / descriptionPrevious value: -"Trading pair, e.g. BTC/USDT, ETH/USDT, SOL/USDT"New value: +"Trading pair in BASE/QUOTE format, e.g. BTC/USDT, ETH/USDT, SOL/USDT." - added
Input schema / properties / symbol / patternAdded value: +"^[A-Z0-9]+/[A-Z0-9]+$" - changed
Input schema / properties / timeframe / descriptionPrevious value: -"Candle timeframe: 1m, 5m, 15m, 1h, 4h, 1d"New value: +"Candlestick timeframe for signal analysis. Defaults to 15m." - added
Input schema / properties / timeframe / enumAdded value: +[ + "1m", + "5m", + "15m", + "1h", + "4h", + "1d" +]
2 tool updates
- First observed
generate_signal - First observed
get_account
Related MCP Connectors
AI crypto signals, whale positions, 19 technical indicators, derivatives, screener and backtests
Crypto market signals, technical indicators, and sentiment analysis for AI agents.
Crypto fundamental analysis, sentiment and whale tracking for traders and AI agents.
Validated trading edges across futures, equities, crypto. Live signals, full audit trail.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAI-Powered Cryptocurrency Direction Prediction & Market Signal AnalysisMIT
- FlicenseNot gradedqualityCmaintenanceLive AI-generated crypto trading signals for agents. Returns coin, direction and confidence with no API key at a ll; a free account adds full reasoning and verified outcomes, and Pro unlocks entry, stop-loss, take-profit and leverage plus 30-d ay history.114-
- AlicenseAqualityAmaintenanceAI-native quantitative trading signal engine for crypto and TradFi perpetuals. Multi-factor composite BUY/SELL/HOLD signals, cross-venue funding rate arbitrage scanning, and market regime detection powered by Hyperliquid data.8208 npm8MIT
- FlicenseNot gradedqualityDmaintenanceProvides cryptocurrency trading signals, market analysis, and portfolio management capabilities across 15+ exchanges with AI-enhanced technical analysis, arbitrage detection, and risk assessment tools.2-
Glama MCP Gateway
Add one secure layer between your agents and this server.