Skip to content

QuantWright MCP server

com.quantwright/agent-apiquantwright.comstreamable-httpv1.0.0Scanned

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

6 tools: 1 do something that can't be undone, 4 change things and 1 only read.

Tools: 0 delete, 1 irreversible, 4 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 1
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the QuantWright MCP server can do

The QuantWright MCP server is published by quantwright.com, a domain the MCP Registry verified. It has 6 tools. It can do things that cannot be undone, such as sending, paying or publishing (create_study) and create or change data (4 tools: describe_data, run_backtest, run_held_out_test and compare_trades), but cannot delete data. 1 tool only reads.

1 tool can send data out of your system (create_study).

The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 10, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Can't be undone 1Claude Code: ask
  • create_studyOpens a study, the named set of runs every backtest belongs to: call it once per question, before run_backtest.Can send data outNo findings

    Why it is in this group

    • The name "create_study" says "create": a word for a change.
    • The input addresses people (input.hold_out.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.hold_out.to): what the tool writes goes there.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Changes things 4Claude Code: ask
  • compare_tradesChecks 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 (al…1 finding

    Why it is in this group

    • The name "compare_trades" says "compare": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "compare_trades" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "compare_trades" says "compare": a word for reading.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • describe_dataStart here to backtest a trading idea.1 finding

    Why it is in this group

    • The name "describe_data" says "describe": a word for reading.
    • The description's first verb is "start": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "describe_data" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "describe_data" says "describe": a word for reading.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • run_backtestBacktests a trading rule on this server's price history: one backtesting.py Strategy class, one symbol, one bar size, in a study.No findings

    Why it is in this group

    • The name "run_backtest" says "run": a word for a change.
    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • run_held_out_testThe final out-of-sample check: runs a finished run's exact code once over its study's hold-out period.No findings

    Why it is in this group

    • The name "run_held_out_test" says "run": a word for a change.
    Description, as the server wrote it
    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`.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 1Show 1 read-only tool
  • get_resultReads 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).No findings

    Why it is in this group

    • The name "get_result" says "get": a word for reading.
    Description, as the server wrote it
    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).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:23 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://quantwright.com/.well-known/oauth-protected-resource/api/mcp
Authorization servers
https://clerk.quantwright.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
yes
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (1 irreversible, 4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://quantwright.com/api/mcp: tools/list returned 6 tools to an anonymous client, including create_study (irreversible), describe_data (write), run_backtest (write), run_held_out_test (write), compare_trades (write)

    What this check looks for

Posture changes

  1. Nov 6, 2026
    • Dynamic client registration: no to yes
    • Client ID metadata documents: no to yes

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The server marks "describe_data" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "describe_data" says "describe": a word for reading.

    What this check looks for
  • The server marks "compare_trades" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "compare_trades" says "compare": a word for reading.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools3 changed.~3 changedView diff
  2. PostureRemote posture changed. Dynamic client registration: no -> yes; Client ID metadata documents: no -> yes.View diff
    • Dynamic client registration: no to yes
    • Client ID metadata documents: no to yes

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-api https://quantwright.com/api/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http agent-api https://quantwright.com/api/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent-api__get_result"
    ],
    "ask": [
      "mcp__agent-api__describe_data",
      "mcp__agent-api__create_study",
      "mcp__agent-api__run_backtest",
      "mcp__agent-api__run_held_out_test",
      "mcp__agent-api__compare_trades"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-api. Review it before you use it.

Capability tags behind 1 rule
  • mcp__agent-api__create_study outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.quantwright/agent-api/verify?hash=9f2552fcf6e2a29a6565635d2ad064b45ccdda105054f5c5570e7e8e51ba9cc2" | jq -e '.changed == false'

Pinned hash 9f2552fcf6e2, from Nov 10, 2026, 22:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.quantwright/agent-api/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.quantwright/agent-api
[![Anlyon Radar](https://radar.anlyon.com/badge/com.quantwright/agent-api.svg)](https://radar.anlyon.com/servers/com.quantwright/agent-api)

Source: MCP Registry. Synced Oct 29, 2026, 13:17 UTC.

QuantWright MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the QuantWright MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 5 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the QuantWright MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the QuantWright MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: create_study.

What tools does the QuantWright MCP server have?

6 tools: 1 irreversible, 4 write, 1 read. create_study, describe_data, run_backtest, run_held_out_test, compare_trades and get_result.

Does the QuantWright MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the QuantWright MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_study.

Has the QuantWright MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.