# QuantWright

> QuantWright is a paid MCP server for finance and payments. Backtest trading strategies written by your agent, with a held-out test that counts once. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Starting price:** $39 a month
- **Platforms:** API, Web
- **Website:** https://quantwright.com/docs/agent-api
- **MCP Registry name:** com.quantwright/agent-api
- **Categories:** finance and payments
- **Listing updated:** 2026-11-15

## About

QuantWright's agent API lets an assistant you run yourself (Claude Code, Codex or another MCP client) write a strategy as a single backtesting.py class. QuantWright runs it in a sandbox on price history it already holds and returns summary figures, so the agent never needs to fetch data. The page is firm that this is research software: it places no orders, results are hypothetical and nothing is investment advice.

The design targets overfitting. A held-out test is meant to be used once, and the score accounts for how many versions were tried. Results show returns, drawdown and win rate but not prices, equity charts or per-trade returns, because the data licence covers results only. Held data includes US stocks and ETFs, spot crypto and spot FX; CME futures are paused.

It is included in the QuantWright subscription (beta price EUR 39 a month excluding VAT) and uses none of the AI allowance, but has daily limits: 50 studies, 150 runs and 30 minutes of engine time, one run at a time. Before keys work you must confirm that your assistant has training turned off or zero data retention with a provider in the US or EU.

## Features

- **Strategy sandbox:** Runs one backtesting.py Strategy class on held price data.
- **Held-out test:** A separate test intended to count once.
- **Version-aware score:** Score that reflects every version tried.
- **Trade comparison:** Compare trades between runs.
- **Summary-only results:** Returns, drawdown and win rate without prices or charts.
- **Key or sign-in access:** Use a bearer API key or MCP sign-in.

## Good for

- Test a strategy idea from Claude Code without downloading data
- Check whether a result survives a held-out test
- Compare two versions of a strategy
- Read earlier results without a new run

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http agent-api https://quantwright.com/api/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://quantwright.com/api/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "agent-api": {
      "url": "https://quantwright.com/api/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "agent-api": {
      "type": "http",
      "url": "https://quantwright.com/api/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "agent-api": {
      "serverUrl": "https://quantwright.com/api/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "agent-api": {
      "type": "http",
      "url": "https://quantwright.com/api/mcp"
    }
  }
}
```

## Tools

- `create_study`: Create a study for a strategy.
- `run_backtest`: Run a backtest of a strategy.
- `run_held_out_test`: Run the held-out test.
- `compare_trades`: Compare trades between runs.
- `get_result`: Read an existing result.
- `describe_data`: Describe the available data.

## FAQ

### Does it place trades?

No. It never places orders and results are hypothetical.

### What does it cost?

It is part of the subscription, EUR 39 per month excluding VAT in the beta; no separate price.

### What limits apply?

50 studies, 150 runs and 30 minutes of engine time a day, and one run at a time.

### What must I confirm first?

That your AI assistant has training off or zero data retention with a US or EU provider.

### Is QuantWright free?

No. QuantWright is a paid product. Paid plans start at $39 a month.

### How do I add QuantWright to Claude Code?

Run this command in your terminal: claude mcp add --transport http agent-api https://quantwright.com/api/mcp

### What are the best alternatives to QuantWright?

The closest alternatives to QuantWright are Solana MCP by Vybe, Tapetide - Indian Stock Market MCP, Budget Tracker, Quantivex Research and Provyan.

## Alternatives

- [Solana MCP by Vybe](https://ai-powered.com/mcp/solana-mcp-by-vybe): Solana MCP by Vybe is an MCP server for finance and payments.
- [Tapetide - Indian Stock Market MCP](https://ai-powered.com/mcp/tapetide-indian-stock-market-mcp): Tapetide - Indian Stock Market MCP is a freemium MCP server for finance and payments.
- [Budget Tracker](https://ai-powered.com/mcp/budget-tracker-2): Budget Tracker is a freemium MCP server for finance and payments.
- [Quantivex Research](https://ai-powered.com/mcp/quantivex-research): Quantivex Research is a free MCP server for finance and payments.
- [Provyan](https://ai-powered.com/mcp/provyan): Provyan is a free MCP server for finance and payments.
- [TribuJus](https://ai-powered.com/mcp/tribujus): TribuJus is an open-source MCP server for legal and government.
- [L2WS](https://ai-powered.com/mcp/l2ws): L2WS is a paid MCP server for finance and payments.
- [Invoices](https://ai-powered.com/mcp/invoices): Invoices is a paid MCP server for files and documents.

---
Source: https://ai-powered.com/mcp/quantwright
