H|ψ⟩ Quantum Finance
Real-Time Stock & Options Analytics for AI Agents
LIVE

HPSILab MCP

Connect your Agent

Connect your AI agent to HPSILab's quantitative finance intelligence.

MCP · OAuth 2.1 · 9 Quant Tools

Account required

Create a free HPSILab account to connect your agent. Every connected agent belongs to an account, and every call is authenticated with an API key.

Create Free Account Sign In
  • 100 trial Credits included.

Once you have an account, point your MCP client at this endpoint:

https://hpsilab.com/mcp
Add HPSILab to your client REST API & SDKs

What your agent gets back

One question, answered from nine quant tools at once — no dashboard, no tab-hopping.

SAMPLEShould I be watching NVDA tomorrow?
Next-day probability
63%
10-day Monte Carlo
$161 – $184
IV regime
Elevated
Options pressure
Call wall nearby

Agent-ready response

NVDA shows a positive directional signal, but the agent should size the idea around elevated volatility and a nearby call wall. Check the earnings calendar and downside band before turning this into an alert or a watchlist entry.

How the connection works

  1. 1

    Create your account

    Sign up free, or sign in if you already have an HPSILab account. There is no connected agent without an account.

  2. 2

    Connect your agent

    Add https://hpsilab.com/mcp to your MCP client. Dynamic Client Registration lets the client register itself — you do not paste anything.

  3. 3

    Authorize

    Your client opens HPSILab sign-in over OAuth 2.1 with PKCE. On approval HPSILab issues an API key to your account and hands it to the client.

  4. 4

    Agent connected

    Your agent calls the tools below with that key. Calls are metered against your account's Credits balance, starting with 100 trial Credits.

Account and API key are always required

What differs is who creates the key, not whether you need one.

MCP / AI Agent

Account + OAuth 2.1 + PKCE + DCR → key issued automatically

Your MCP client registers itself and completes the authorization flow. HPSILab creates the API key and gives it to the client, so you never create or paste one by hand.

REST API / SDK

Account + API key you create

REST, the Python SDK and the TypeScript SDK send a key you create yourself in Settings as 'Authorization: Bearer <key>'.

Create an API key

Add HPSILab to your client

Any MCP client that speaks streamable HTTP can connect. On first use it opens HPSILab sign-in — sign in with the account you just created.

Claude Code

Run this in your terminal, then /mcp in Claude Code to authorize.

claude mcp add --transport http hpsilab https://hpsilab.com/mcp

Claude

Open

Settings → Connectors → Add custom connector, then paste the endpoint.

https://hpsilab.com/mcp

ChatGPT

Open

Settings → Connectors → Add custom connector, then paste the endpoint. Requires a plan with custom connectors enabled.

https://hpsilab.com/mcp

Cursor

Open

Opens Cursor and pre-fills the HPSILab server. Approve it in Settings → MCP.

https://hpsilab.com/mcp

VS Code

Open

Opens VS Code and adds the server to your MCP configuration.

https://hpsilab.com/mcp

Codex CLI

Add to ~/.codex/config.toml. The mcp-remote bridge also works for any other stdio-only client.

[mcp_servers.hpsilab]
command = "npx"
args = ["-y", "mcp-remote", "https://hpsilab.com/mcp"]

Any MCP client

The standard remote-server config block. Drop it into your client's MCP settings file.

{
  "mcpServers": {
    "hpsilab": {
      "url": "https://hpsilab.com/mcp"
    }
  }
}

Tools your agent gets

9

Read live from the MCP server's tools/list.

  • get_iv_radar

    Implied-volatility (IV) structure for a stock: how expensive options are, whether volatility is being squeezed, and whether traders are paying up for upside (calls) or downside (puts).

  • get_monte_carlo

    Monte Carlo price simulation for the next ~10 trading days: thousands of random price paths estimate a likely price range and the odds of finishing higher.

  • get_ai_prediction

    AI next-day prediction: probability the stock closes UP, a plain buy/watch/sell-lean signal, and how strongly the models agree (consensus).

  • get_equity_curve

    Backtest performance of the quant strategy across your watchlist: Sharpe ratio, max drawdown, win rate and total return per symbol.

  • get_option_pressure

    Option-chain pressure map for the nearest weekly/monthly expiry — Max Pain, dealer Gamma Wall, likely weekly high, and an extreme squeeze target.

  • analyze_stock

    Aggregate all quant tools into one JSON stock analysis.

  • get_pretrade_risk_scan

    Full pre-trade risk scan JSON for a stock.

  • generate_stock_images

    Generate stock-report PNG images and return their URLs.

  • generate_stock_research_report

    Full markdown research report with five stock-report charts.

Authorization

HPSILab implements OAuth 2.1 with Dynamic Client Registration. Your client discovers all of this automatically — the values are here so you can verify them.

Resource metadata
https://hpsilab.com/.well-known/oauth-protected-resource/mcp
Authorization server
https://hpsilab.com/.well-known/oauth-authorization-server
Registration (DCR)
https://hpsilab.com/oauth/register
Authorize
https://hpsilab.com/oauth/authorize
Token
https://hpsilab.com/oauth/token
PKCE
S256 (required)

Start with 100 trial Credits

Every new account gets trial Credits, so your agent's first calls work immediately after authorization.

Create Free AccountBrowse the tools on the web

HPSILab provides quantitative research and market data for information only. Nothing on this page or returned through the MCP server is investment advice, a recommendation, or a solicitation to buy or sell. An AI agent acts on the permissions and strategy you give it — the decisions, and the risk, remain yours.

Connect your Agent | HPSILab MCP