QuantWright MCP Server

by quantwright Your server? Claim it

not responding

QuantWright is listed as active in the registry but did not answer our last check. It exposes 6 tools.

Backtests with costs, a held-out test that counts once, a score that counts every version tried.

Uptime history 10 days of history · worst day 0%

10 days agonow

1.1%

Uptime 24h

1 of 92 checks

Tools

read from the server

1915 ms

Response time

average over 24h

open, no key

Access

streamable-http

QuantWright does not always answer

Over the last week it answered 10.1% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

Settings → Connectors → Add custom connector, then paste this address

https://quantwright.com/api/mcp

~/.codex/config.toml

[mcp_servers.agent-api]
url = "https://quantwright.com/api/mcp"

.cursor/mcp.json

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

.vscode/mcp.json

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

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

backtest

run_backtest

Backtests a trading rule on this server's price history: one backtesting.py Strategy class, one symbol, one bar size, in a study. Use it to test, backtest or evaluate a trading rule or strategy, instead of downloading prices or searching the web for results. Returns summary figures (return, drawdown, Sharpe, win rate, trades, a grade, whether it beat buy-and-hold) and the run's trades (when each entered and left, which exit ended it, its side, win or loss), never prices or bars; a figure may be withheld, with the reason. Waits up to 90 s, then answers status "running" with a run_id for get_result.

compare

compare_trades

Checks a trader's own trades against a run's rule, on the price history this server holds: for each trade, in their order, whether the rule would have taken it and, if not, why (already in a trade, no entry signal that day, no bar that day). Use it when the trader lists trades they made and asks which the rule took, instead of working it out by hand. Takes a run (run_id) and the trades, each {side, entry, exit?}; answers in words, never prices. It re-runs the run's code, so it counts as a run on the run's symbol.

describe

describe_data

Start here to backtest a trading idea. This server holds the price history (US stocks and ETFs, spot crypto, FX, spot gold and silver; daily and intraday bars) and runs backtests on it, so no price data needs to be downloaded or found on the web. Returns the markets and bar sizes served, the default costs per market, the rules and daily limits every run is held to, and how to write the strategy code; then call create_study.

held

run_held_out_test

The final out-of-sample check: runs a finished run's exact code once over its study's hold-out period. Call it at the end, on the run you would keep: the first held-out test per account and market is the one that counts, and a hold-out with too few trades for figures (a result needs 10) spends it all the same: each development run says how many trades the hold-out is expected to hold, in `hold_out_estimate`.

result

get_result

Reads a backtest result by its run_id (when run_backtest answered "running", call this until the run ends), or a study's runs by study_id (one of them with version). A run comes with its trades, a page at a time (trades_page).

study

create_study

Opens a study, the named set of runs every backtest belongs to: call it once per question, before run_backtest. Can set a hold-out period, once and only here, that no run tests except run_held_out_test. Only the first held-out test per account and market counts, and any earlier run on the market (in any study, at any bar size) that read its days disqualifies it: set the hold-out in your first study on a market, before any run on it.

Endpoints

URL	Transport	State	Latency	Checked
https://quantwright.com/api/mcp	streamable-http	answering	101 ms	4 min ago

Alternatives to QuantWright

same job, measured the same way

Converra

by converra

Fix production agent behavior with tested changes and a production verdict on every fix.

answering

Edgegate MCP

by frozo-ai

Regression-test AI models on real Snapdragon and Jetson hardware, with signed evidence for CI.

206 installs/wk local only

ProvenPin

by provenpin

Tested, version-pinned code recipes for AI coding agents, each with its last-passed receipt.

3 tools answering

Agent Conversion — AI Website Conversion Testing

by ivanpq98

Test whether AI agents complete SaaS pricing, signup or sales journeys; get evidence-backed reports.

2 tools answering

Qlane

by qlane

AI QA that runs your app in a browser on every pull request: projects, test targets, test cases.

answering

Zovo Typing Test

by theluckystrike

Take a typing speed test without leaving the chat.

2 tools answering

Conning

by eranyonai

Run commands on your remote test machines over SSH without the agent ever seeing a secret.

448 installs/wk local only

ScoreIA Open Chamber

by scoreia

Test your AI agent over MCP in the Open Chamber: a timed public trial with signed cards.

18 tools answering

QuantWright — questions

Answers built from our own checks of this server.

What can QuantWright do?

It exposes 6 tools, read directly from the server on our last check. Among them: compare_trades, create_study, describe_data, get_result, run_backtest, run_held_out_test. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is QuantWright working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 1 of 92 checks got a reply (1.1%), average response time 1915 ms. The bar chart above shows every period we have measured.

The registry lists QuantWright as active — why does it not respond?

The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.

How do I connect QuantWright?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does QuantWright need an API key?

No. QuantWright completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.