Skip to content
MCP server

QuantWright

Backtest trading strategies written by your agent, with a held-out test that counts once

Install
Pricing
Paid
Platforms
API, Web
Runs
Remotely
Version
1.0.0
Listing updated
2 days ago

About QuantWright

QuantWright is a paid MCP server for finance and payments. It runs as a hosted remote server, so there is nothing to install locally.

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.

Install

Run in a terminal

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

Add to Settings → Connectors → Add custom connector

https://quantwright.com/api/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "agent-api": {
      "url": "https://quantwright.com/api/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

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

Add to ~/.codeium/windsurf/mcp_config.json

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

Add to your client's MCP settings (most use this shape)

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

Tools this server provides (6)

Taken from the project documentation; the running server may differ.

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.

What it does

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

Pricing

Paid, from $39 a month

Part of the QuantWright subscription: EUR 39 per month excluding VAT during the beta; 14-day money-back on the first payment

Prices change. Check quantwright.com before you buy.

QuantWright 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 to QuantWright

  1. Remote MCP server exposing the Vybe Solana API to AI clients and code editors

    • 44 tools
    • Remote
    • 2.8K GitHub stars
    • Finance and payments
  2. Indian NSE and BSE stock market data for AI assistants through 48 MCP tools

    • 17 tools
    • Remote
    • Freemium
    • 150 GitHub stars
    • Finance and payments
  3. Budget Tracker

    MCP server

    Local MCP expense ledger that logs receipts and mileage, splits VAT and prepares rebilling

    • 14 tools
    • Remote
    • Freemium
    • 2 GitHub stars
    • Finance and payments
  4. Stock scores, what a price assumes, earnings quality and quiet profit revisions

    • 11 tools
    • Remote
    • Free
    • Finance and payments
  5. Provyan

    MCP server

    Backtested crypto signal results on 94 coins, with luck odds and sources

    • 4 tools
    • Remote
    • Free
    • Finance and payments
  6. TribuJus

    MCP server

    Read-only access to UK bank accounts, cards and transactions via TrueLayer Open Banking

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • Legal and government