QuantLogix MCP Server

Connect QuantLogix to your AI tools — Claude Desktop, Cursor, Claude Code, or any MCP-aware client. Ask "What's the signal on NVDA?" or "Show me Berkshire's latest 13F" right where you already work.

Requires a Pro or Institutional API key. The MCP server uses the same ql_... keys as the public REST API. Get one from the API Keys card on your profile.

Endpoint

The MCP server speaks JSON-RPC 2.0 over HTTP at a single URL:

https://quantlogix.ai/api/mcp/v1

Protocol version: 2025-06-18 · Transport: streamable-http · Auth: Authorization: Bearer ql_...

Setup

Pick your client. The config snippets below all assume your key is in an environment variable called QUANTLOGIX_API_KEY — you can also paste the key inline if you prefer.

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop:

{
  "mcpServers": {
    "quantlogix": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://quantlogix.ai/api/mcp/v1",
        "--header",
        "Authorization:Bearer ${QUANTLOGIX_API_KEY}"
      ],
      "env": {
        "QUANTLOGIX_API_KEY": "ql_paste_your_key_here"
      }
    }
  }
}

After restart, you'll see quantlogix in the 🔌 connectors menu with all 11 tools listed. Ask "What's QuantLogix's signal for AMD?" to test.

From any project directory, run:

claude mcp add quantlogix https://quantlogix.ai/api/mcp/v1 \
  --header "Authorization: Bearer $QUANTLOGIX_API_KEY"

Or add to .mcp.json in the project root:

{
  "mcpServers": {
    "quantlogix": {
      "type": "http",
      "url": "https://quantlogix.ai/api/mcp/v1",
      "headers": {
        "Authorization": "Bearer ql_paste_your_key_here"
      }
    }
  }
}

Add to .cursor/mcp.json in your project (or ~/.cursor/mcp.json for global):

{
  "mcpServers": {
    "quantlogix": {
      "url": "https://quantlogix.ai/api/mcp/v1",
      "headers": {
        "Authorization": "Bearer ql_paste_your_key_here"
      }
    }
  }
}

Restart Cursor. The tools appear in the Composer / Chat tool list.

List available tools:

curl -s https://quantlogix.ai/api/mcp/v1 \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Call a tool (requires a Pro+ key):

curl -s https://quantlogix.ai/api/mcp/v1 \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ql_paste_your_key_here" \
  -d '{
    "jsonrpc":"2.0",
    "id":2,
    "method":"tools/call",
    "params":{
      "name":"signal",
      "arguments":{"ticker":"NVDA"}
    }
  }'

Available Tools

The MCP server exposes 11 tools wrapping the QuantLogix public REST API. The tier badge shows the minimum subscription required — each tool inherits the same gate as its underlying /api/v1/* endpoint.

signal Pro Long-term 5-factor composite signal — BUY/NEUTRAL/SELL label, score 0-100, factor breakdown (technical, momentum, fundamental, options, microstructure), pattern prediction.

day_signal Institutional Intraday QDTSS signal — 4-layer scoring with VWAP, ORB, session classifier, concrete trade plan. Minutes-to-hours horizon.

swing_signal Institutional Swing-trading signal — A/B/C/D conviction grade + 3-pillar breakdown (Technical / Options-Flow / Sentiment). 2 days to 4 weeks horizon.

microstructure Institutional VPIN, Kyle's lambda, order-flow imbalance, smart-money score, institutional bias, volume profile, bid-ask spread.

news Pro Aggregated news across 14 publishers with per-article sentiment.

institutional_holders Pro Top 13F holders for a ticker — Berkshire, BlackRock, Vanguard, Renaissance, Citadel, Bridgewater, Tiger Global, Pershing Square, etc.

fund_holdings Pro Full 13F portfolio for a fund by SEC CIK.

private_companies_list Pro Curated list of ~30 top private (pre-IPO) companies: Anthropic, OpenAI, Stripe, Databricks, Anduril, Perplexity, Mistral, etc.

private_company Pro Full profile for one private company by slug — valuation, funding history, investors.

private_company_news Pro Multi-source live news for a private company.

engine_model_card Pro The engine's model card — measured win-rate + return, the four statistical-validation grades (significance · calibration · discrimination · robustness), and per-factor walk-forward IC health, computed on the immutable track record. The live numbers behind quantlogix.ai/proof.

Rate Limits

Tier	Per minute	Per month	Tool access
Pro $149/mo	60	10,000	8 tools (long-horizon + model card)
Institutional $299/mo	300	Unlimited	All 11 tools (incl. intraday)

Limits are enforced inside each /api/v1/* endpoint — the MCP layer is a pass-through. Same headers (X-RateLimit-Limit, X-RateLimit-Monthly) come back on every tools/call response.

Example Prompts

Once connected, try asking your AI tool:

"Pull QuantLogix's signal for NVDA and explain the factor breakdown."
"Compare the QuantLogix swing signals for AMD, NVDA, and AVGO."
"Who are the top institutional holders of TSLA according to QuantLogix?"
"List private companies in the AI sector and show me OpenAI's latest news."
"Get QuantLogix's intraday day-signal for SPY and tell me the trade plan."

Get Started

You'll need an active Pro or Institutional subscription, then a key from the API Keys card on your profile.

Get an API Key View Pricing REST API Docs

Protocol Notes

The QuantLogix MCP server implements:

initialize — handshake, returns server info + capabilities
tools/list — returns all 11 tools with JSON Schema
tools/call — execute a tool, returns content array
ping — health check

Tool calls require Authorization: Bearer ql_.... The initialize, ping, and tools/list methods are public so clients can probe the server without a key. Upstream errors (rate limit, invalid ticker, tier gate) come back as MCP isError content so the AI can recover and explain to the user in-conversation, rather than crashing the client.

Questions or feedback? Contact our team.