Documentation

◆ Quick Start

Add AlgoVault to Claude Desktop in under 30 seconds. Paste this into your claude_desktop_config.json:

{
  "mcpServers": {
    "crypto-quant-signal": {
      "command": "npx",
      "args": ["-y", "crypto-quant-signal-mcp"]
    }
  }
}

Then ask Claude:

Free tier: all 716 assets, all 11 timeframes (1m–1d), 100 calls/month. No signup needed. Upgrade to Starter ($9.99/mo) or Pro for higher monthly limits and unlimited funding-arb results.

Your agent can also ask AlgoVault to teach itself how to use the tools — see Knowledge Tools below.

Testing with raw HTTP / curl

If you want to test your API key without an MCP client (Claude Desktop, Cursor, Claude Code), the MCP Streamable HTTP protocol requires a 3-step handshake before tools/call:

AV_KEY="av_live_..."   # paste your API key

# 1. initialize — captures session-id from response headers
SESSION_ID=$(curl -sS -i -X POST https://api.algovault.com/mcp \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AV_KEY" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"curl","version":"1.0"}},"id":1}' \
  | awk 'BEGIN{IGNORECASE=1} /^mcp-session-id:/ {gsub(/\r/,""); print $2; exit}')

# 2. notify "initialized" (required by MCP protocol)
curl -sS -X POST https://api.algovault.com/mcp \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AV_KEY" \
  -H "Accept: application/json, text/event-stream" \
  -H "mcp-session-id: $SESSION_ID" \
  -d '{"jsonrpc":"2.0","method":"notifications/initialized"}' >/dev/null

# 3. now call tools/call
curl -sS -X POST https://api.algovault.com/mcp \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AV_KEY" \
  -H "Accept: application/json, text/event-stream" \
  -H "mcp-session-id: $SESSION_ID" \
  -d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"get_trade_call","arguments":{"coin":"SOL","timeframe":"5m","exchange":"BINANCE"}},"id":2}'

Most users won't need this — Claude Desktop / Cursor / Claude Code MCP clients handle the handshake automatically. Use this only for direct integration into a non-MCP system or for debugging.

◆ get_trade_call (alias: get_trade_signal)

Returns a composite BUY/SELL/HOLD trade call with confidence percentage, regime context, and reasoning across 5 exchanges.

Parameters

Example Response

{
  "call": "BUY",
  "confidence": 78,
  "price": 84250.50,
  "indicators": {
    "funding_rate": 0.0001,
    "funding_24h_avg": 0.00008,
    "funding_state": "NORMAL",
    "oi_change_pct": 2.4,
    "volume_24h": 2381602633,
    "trend_persistence": "HIGH",
    "breakout_pending": "INACTIVE"
  },
  "regime": "TRENDING_UP",
  "reasoning": "Trending regime, upward bias. Funding pressure mild. Volatility neither expanding nor compressed. Trend persistence elevated; momentum structure. Strong conviction from aligned signals.",
  "timestamp": 1712764800,
  "coin": "BTC",
  "timeframe": "1h",
  "_algovault": {
    "version": "1.10.0",
    "tool": "get_trade_call",
    "compatible_with": ["crypto-quant-risk-mcp", "crypto-quant-backtest-mcp"]
  }
}

◆ scan_funding_arb

Scans cross-venue funding rate differences between Hyperliquid, Binance, and Bybit. Returns top arbitrage opportunities ranked by annualized spread.

Parameters

Example Response

{
  "opportunities": [
    {
      "coin": "ETH",
      "rates": {
        "HlPerp": 0.000125,
        "BinPerp": -0.000042,
        "BybitPerp": -0.000038
      },
      "bestArb": {
        "longVenue": "Binance",
        "shortVenue": "Hyperliquid",
        "spreadBps": 13.4,
        "annualizedPct": 117.3,
        "direction": "Long Binance / Short Hyperliquid"
      }
    }
  ],
  "scannedPairs": 245,
  "timestamp": 1712764800,
  "_algovault": {
    "version": "1.10.0",
    "tool": "scan_funding_arb",
    "compatible_with": ["crypto-quant-risk-mcp", "crypto-quant-execution-mcp"]
  }
}

◆ get_market_regime

Classifies the current market regime for any asset across 5 exchanges. Returns one of four states: TRENDING_UP, TRENDING_DOWN, RANGING, or VOLATILE.

Parameters

Example Response

{
  "regime": "TRENDING_UP",
  "confidence": 85,
  "metrics": {
    "adx_interpretation": "Strong trend",
    "volatility_interpretation": "Normal",
    "price_structure": "HIGHER_HIGHS",
    "trend_strength": "STRONG",
    "cross_venue_funding_sentiment": "BULLISH_BIAS",
    "funding_divergence_note": "HL funding 3.2x above CEX avg — longs concentrated on HL"
  },
  "suggestion": "Strong uptrend detected. Favor long positions with trend-following strategies.",
  "timestamp": 1712764800,
  "coin": "BTC",
  "timeframe": "4h",
  "_algovault": {
    "version": "1.10.0",
    "tool": "get_market_regime",
    "compatible_with": ["crypto-quant-risk-mcp", "crypto-quant-backtest-mcp"]
  }
}

◆ Knowledge Tools

Two MCP tools that let your AI agent learn how to use AlgoVault before calling the trading tools. Search the docs lexically; ask synthesized questions; never invent a parameter shape again.

◆ What are knowledge tools

Most MCP-aware agents read tools/list once, then invent parameter shapes when calling tools. AlgoVault ships two meta-tools that let an agent self-serve documentation instead:

• search_knowledge — BM25 lexical search over every tool description, response shape, integration tutorial, and code example.
• chat_knowledge — natural-language answer with citations, grounded in the same bundle.

Both tools query a knowledge bundle auto-rebuilt within 30 seconds of every release — no stale answers.

◆ 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.

Parameters

◆ 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).

Parameters

◆ When to use which

◆ Worked examples

1. Discovery query — agent asks for trade-call docs before calling get_trade_call:

search_knowledge({
  query: "how do I get a trade call with stop loss for BTC"
})
// → ranked snippets including get_trade_call describe-text + integration excerpts

2. Comparison query — ask for synthesis across two tool descriptions:

chat_knowledge({
  question: "what's the difference between get_trade_call and get_market_regime"
})
// → synthesized answer with [source: ...] citations

3. Integration discovery — agent finds the LangChain tutorial:

search_knowledge({
  query: "how do I integrate with LangChain"
})
// → LangChain integration tutorial ranks first, with full code snippet

4. Direct HTTP — search:

curl -X POST https://api.algovault.com/api/search \
  -H "Content-Type: application/json" \
  -d '{"query":"BTC stop loss","limit":3}'

# → { "query": "BTC stop loss", "total_results": 3, "results": [...], "_algovault": {...} }

5. Direct HTTP — chat:

curl -X POST https://api.algovault.com/api/chat \
  -H "Content-Type: application/json" \
  -d '{"question":"how do I get a BTC trade call","model":"claude-haiku-4-5-20251001"}'

# → { "question": "...", "answer": "...", "citations": [...], "model": "...", "_algovault": {...} }

◆ HTTP API

Both tools also expose plain HTTP endpoints for non-MCP consumers. No streamable-HTTP handshake required — just POST with JSON body.

Error contract: INVALID_QUERY / QUERY_TOO_SHORT / QUERY_TOO_LONG / INVALID_QUESTION / QUESTION_TOO_SHORT / QUESTION_TOO_LONG / INVALID_MODEL / CHAT_QUOTA_EXHAUSTED / INTERNAL_ERROR. All return JSON {"code": "...", "message": "..."}.

◆ Rate limits & cost

Cost transparency: chat_knowledge costs about $0.002 per call with prompt caching. Quota resets at the first of each UTC month.

◆ Integration

Drop AlgoVault into any MCP-compatible client, any major agent framework, or any exchange Agent Trade Kit. Pick your path below.

◆ Connect Your MCP Client

Your av_live_… API key works across every MCP-compatible client. Pick yours below. Free tier (no key) also works for every coin + every timeframe, capped at 100 calls/month.

{
  "mcpServers": {
    "algovault": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.algovault.com/mcp",
               "--header", "Authorization: Bearer ${AV_API_KEY}",
               "--header", "X-AlgoVault-Track-Token:chan-docs"]
    }
  }
}

{
  "mcpServers": {
    "algovault": {
      "url": "https://api.algovault.com/mcp",
      "headers": {
        "Authorization": "Bearer ${env:AV_API_KEY}",
        "X-AlgoVault-Track-Token": "chan-docs"
      }
    }
  }
}

{
  "mcpServers": {
    "algovault": {
      "type": "streamableHttp",
      "url": "https://api.algovault.com/mcp",
      "headers": {
        "Authorization": "Bearer ${env:AV_API_KEY}",
        "X-AlgoVault-Track-Token": "chan-docs"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

claude mcp add --transport http --scope project algovault https://api.algovault.com/mcp \
  --header "Authorization: Bearer $AV_API_KEY" \
  --header "X-AlgoVault-Track-Token:chan-docs"

{
  "mcpServers": {
    "algovault": {
      "type": "http",
      "url": "https://api.algovault.com/mcp",
      "headers": {
        "Authorization": "Bearer ${AV_API_KEY}",
        "X-AlgoVault-Track-Token": "chan-docs"
      }
    }
  }
}

# Pick one — replace <client> with: claude, cursor, cline, claude-code
npx -y @smithery/cli install crypto-quant-signal-mcp --client <client>

curl -sS https://api.algovault.com/health

Config formats verified 2026-04-30 against: MCP quickstart · Cursor MCP docs · Cline remote-server docs · Claude Code MCP docs · @smithery/cli on npm. Config formats can drift — if a snippet here doesn't work, please refer to the upstream doc and report it at GitHub issues.

◆ Connect Your AI Agent

Building on a major agent framework? AlgoVault MCP plugs into 4 of them via the framework's canonical MCP-adapter library. Each pairing ships with a runnable Python demo.

pip install langchain-mcp-adapters

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({"algovault": {
    "url": "https://api.algovault.com/mcp",
    "transport": "streamable_http"}})
tools = await client.get_tools()
verdict = await tools[0].ainvoke({"coin": "BTC", "timeframe": "4h"})

pip install llama-index-tools-mcp

from llama_index.tools.mcp import BasicMCPClient

client = BasicMCPClient("https://api.algovault.com/mcp")
result = await client.call_tool(
    "get_trade_call", {"coin": "BTC", "timeframe": "4h"})

pip install agent-framework

from agent_framework import MCPStreamableHTTPTool

tool = MCPStreamableHTTPTool(
    name="algovault",
    url="https://api.algovault.com/mcp",
    load_prompts=False)
async with tool:
    contents = await tool.call_tool(
        "get_trade_call", coin="BTC", timeframe="4h")

pip install crewai 'crewai-tools[mcp]'

from crewai_tools import MCPServerAdapter

server_params = {"url": "https://api.algovault.com/mcp",
                 "transport": "streamable-http"}
with MCPServerAdapter(server_params) as tools:
    raw = tools[0].run(coin="BTC", timeframe="4h", exchange="BINANCE")

Tutorials verified 2026-05-18 against: langchain-mcp-adapters · llama-index-tools-mcp · agent-framework · crewAI-tools MCP. Snippets can drift — if one doesn't work, please refer to the upstream doc and report it at GitHub issues.

Try a framework integration: algovault.com/integrations/langchain

◆ Connect Your Exchange Kit

Already running an exchange's Agent Trade Kit? Pair AlgoVault's composite verdict with the kit's execution layer. AlgoVault returns analytics; the exchange kit places orders; your agent decides.

claude plugin install AlgoVaultLabs/algovault-skills
claude plugin install binance/binance-skills-hub

{
  "mcpServers": {
    "algovault": {"url": "https://api.algovault.com/mcp"},
    "okx-trade": {"command": "npx", "args": ["-y", "@okx_ai/okx-trade-mcp"]}
  }
}

{
  "mcpServers": {
    "algovault": {"url": "https://api.algovault.com/mcp"},
    "bybit-trade": {"command": "npx", "args": ["-y", "bybit-official-trading-server"]}
  }
}

{
  "mcpServers": {
    "algovault": {"url": "https://api.algovault.com/mcp"},
    "bitget-trade": {"command": "npx", "args": ["-y", "bitget-mcp-server"]}
  }
}

git clone https://github.com/gemini/developer-platform
cd developer-platform/packages/mcp-server
npm install
npm run build

curl --proto '=https' --tlsv1.2 -LsSf https://github.com/krakenfx/kraken-cli/releases/latest/download/kraken-cli-installer.sh | sh
kraken mcp -s all

{
  "mcpServers": {
    "algovault": {"url": "https://api.algovault.com/mcp"},
    "alpaca": {"command": "uvx", "args": ["alpaca-mcp-server"]}
  }
}

Tutorials verified 2026-05-19 against: Binance Skills Hub · @okx_ai/okx-trade-mcp · bybit-official-trading-server · bitget-mcp-server. Snippets can drift — if one doesn't work, please refer to the upstream doc and report it at GitHub issues.

Try an exchange integration: algovault.com/integrations/binance

◆ On-Chain Verification

Every call is hashed and anchored on Base L2 via daily Merkle batches. This makes the track record tamper-proof.

How It Works

Verification Endpoints

GET /api/verify-signal?signalId=<ID>

GET /api/merkle-batches

Visual Verification

Visit algovault.com/verify to look up any call and see its on-chain proof in a human-readable format.

Contract Details

What This Proves

• ✓ Calls were recorded BEFORE outcomes were known
• ✓ No call can be retroactively edited or deleted
• ✓ The complete set of calls in each batch is locked — cherry-picking is detectable via sequential call IDs

◆ Skills & Usage Examples

20 real-world workflows for AI agents and human developers. From simple one-liners to multi-agent orchestration.

◆ Pricing & Limits

Two payment rails: Stripe subscriptions for human developers, x402 micropayments (USDC on Base) for autonomous agents.

Subscription Tiers

Free HOLD Policy

What happens after you subscribe

x402 Pay-Per-Call (USDC on Base)

No signup. No API key. Your agent pays per call with USDC on Base. Works with any x402-compatible wallet.

◆ FAQ