# AlgoVault — Crypto Quant Trade Calls MCP server

The Brain Layer for AI Trading Agents — quant calls + cross-venue arb across 5 exchanges via MCP.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-algovaultfi-crypto-quant-signal-mcp
- Repository: https://github.com/AlgoVaultLabs/crypto-quant-signal-mcp
- Website: https://algovault.com

## Install
- Command: `npx -y crypto-quant-signal-mcp`
- Endpoint: https://api.algovault.com/mcp
- Auth: Not captured

## Setup notes
- Package: Npm crypto-quant-signal-mcp v1.14.0
- Remote endpoint: https://api.algovault.com/mcp

## Tools
- get_trade_call - Composite verdict BUY SELL HOLD trade call for crypto perpetual futures on Binance Bybit OKX Bitget Hyperliquid. Returns verdict, confidence, market regime, funding rate, reasoning. Verified track record, merkle anchor on Base — on-chain verified. MCP tool for trading. Cross-venue multi-exchange AI trading signal for Claude trading agents. Endpoint: https://api.algovault.com/mcp
- get_trade_signal - Composite verdict BUY SELL HOLD trade call for crypto perpetual futures on Binance Bybit OKX Bitget Hyperliquid. Returns verdict, confidence, market regime, funding rate, reasoning. Verified track record, merkle anchor on Base — on-chain verified. MCP tool for trading. Cross-venue multi-exchange AI trading signal for Claude trading agents. [ALIAS] This tool is an alias of get_trade_call — same behavior, kept for backward compatibility. Endpoint: https://api.algovault.com/mcp
- scan_funding_arb - Cross-venue funding arbitrage scanner. Funding rate spreads across Binance Bybit OKX Bitget Hyperliquid perpetual futures — long one, short other. Composite verdict, multi-exchange funding intelligence. MCP tool for trading. AI trading signal for crypto quant + Claude trading agents. Verified track record, on-chain verified merkle anchor on Base. Endpoint: https://api.algovault.com/mcp
- get_market_regime - Market regime classifier — TRENDING_UP TRENDING_DOWN RANGING VOLATILE — for crypto perpetual futures on Binance Bybit OKX Bitget Hyperliquid. Composite verdict blends trend ranging signals, volatility, cross-venue funding rate sentiment. Returns label, confidence, strategy hint. MCP tool for trading. Verified track record, merkle anchor on Base. Endpoint: https://api.algovault.com/mcp
- search_knowledge - Ask AlgoVault any question about its MCP tools, response shapes, integration patterns (LangChain / LlamaIndex / MAF / CrewAI), or code examples. Returns ranked snippets from the canonical knowledge bundle. Use this BEFORE attempting any tool call to confirm correct parameter usage and avoid hallucinating tool shapes. Fast (BM25 lexical search, no LLM call, no quota cost). For natural-language synthesized answers, use chat_knowledge instead. Endpoint: https://api.algovault.com/mcp
- chat_knowledge - Ask AlgoVault a natural-language question — get a synthesized answer with citations, grounded in the canonical knowledge bundle (every MCP tool description, response shape, integration tutorial, and code example). Use this when you need an explanation, code pattern, or "how do I" answer. For raw ranked snippets without LLM synthesis, use search_knowledge (faster, no quota cost). Quota: Free 10/month, Starter 50/month, Pro 200/month, Enterprise 2000/month. Endpoint: https://api.algovault.com/mcp

## Resources
- analytics://usage-stats - Request analytics — call counts, tool breakdown, tier distribution, top assets, response times. Requires Pro or higher.
- performance://signal-performance - Signal track record — PFE win rates by timeframe, asset, tier, and signal type. Measures whether price moved in the signal direction during the evaluation window.
- mcp://algovault/venues - Per-venue lifecycle state machine: shadow / promoted / retired. Each venue carries asset_count, min_buy_sell_sample, integration timestamp, and last evaluation stats. New venues default to 'shadow' (experimental — not yet on the public /track-record dashboard) and auto-promote via daily cron when PFE WR ≥0.80 over asset_count×10 BUY/SELL signals (HOLDs excluded). Agents querying with a shadow venue's exchange_id should surface an 'experimental' caveat to the end user. MIME type: application/json
- analytics://skills - Per-Skill invocation counters (calls_24h, calls_7d, calls_all_time, first/last seen) for the algovault-skills plugin. Public — slug-level aggregates only.
- algovault://knowledge/latest - AlgoVault knowledge bundle (latest version) — every MCP tool description, response shape, integration tutorial, and code example, indexed for LLM consumption. MIME type: application/json
- algovault://knowledge/algovault-knowledge-v1.16.0 - AlgoVault knowledge bundle for v1.16.0 (version-pinned). MIME type: application/json

## Prompts
Not captured

## Metadata
- Owner: io.github.AlgoVaultFi
- Version: 1.16.0
- Runtime: Npm
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 19, 2026
- Source: https://registry.modelcontextprotocol.io