Skip to content

PropPassCheck MCP server

com.proppasscheck/prop-firm-toolsproppasscheck.comstreamable-httpv3.0.0Scanned

Prop firm challenge rules, pass odds from your own trades, fees and rule changes. No affiliates.

13 tools: 10 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 10 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

10 tools here change things. Govern them.

  • 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 PropPassCheck MCP server can do

The PropPassCheck MCP server is published by proppasscheck.com, a domain the MCP Registry verified. It has 13 tools. It can create or change data (10 tools: compare_challenges, rule_changes, test_trades, test_stats and 6 more), but cannot delete data. 3 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

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.

Last scanned Nov 14, 2026, version 3.0.0.

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.

13 tools

Changes things 10Claude Code: ask
  • check_overlapFor a trader running two to five strategies on the same account.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    For a trader running two to five strategies on the same account. Merges their trades by date and reports how often they trade and lose on the same day, the worst day together against alone, whether they tend to win and lose together, and the odds together against each strategy alone on up to three accounts. Every trade needs a close date. Each strategy's profits are scaled from its own starting balance.

    Annotations the server declares

    • title: Test several strategies together on one account
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • compare_challengesPuts two to six accounts side by side, rule by rule, and marks the rules that differ.1 finding

    Why it is in this group

    • The name "compare_challenges" says "compare": a word for reading.
    • The description's first verb is "put": 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 "compare_challenges" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

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

      What this check looks for
    Description, as the server wrote it
    Puts two to six accounts side by side, rule by rule, and marks the rules that differ.

    Annotations the server declares

    • title: Compare challenges side by side
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • find_best_sizeRuns the same trades (or headline numbers) at eight trade sizes, from a quarter to three times, against up to three accounts, and shows the pass and first-payout chance at each wit…1 finding

    Why it is in this group

    • The name "find_best_size" says "find": a word for reading.
    • The description's first verb is "run": 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 "find_best_size" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "find_best_size" says "find": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Runs the same trades (or headline numbers) at eight trade sizes, from a quarter to three times, against up to three accounts, and shows the pass and first-payout chance at each with the best size marked. Answers "should I risk less or more per trade on this challenge?". Give trades with starting_balance, or the four headline numbers.

    Annotations the server declares

    • title: Find the trade size with the best odds
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • fix_strategyRetests a trader's own closed trades on up to three accounts with a daily stop at several levels and with a cap of one to three trades a day (guards the PropPassCheck strategy buil…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Retests a trader's own closed trades on up to three accounts with a daily stop at several levels and with a cap of one to three trades a day (guards the PropPassCheck strategy builder can add to an EA, or a trader can follow by hand), and reports the one that lifts the chance of passing (or of a first payout on instant accounts) the most, with how much and a link to build it. Needs real trades with starting_balance; give dates when known so each day's trades stay together.

    Annotations the server declares

    • title: Find a guard that lifts the odds
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • funded_lifeFor up to five accounts: the chance of getting funded, then what the funded account does over its first six months (126 trading days): payouts on average, money to the trader after…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    For up to five accounts: the chance of getting funded, then what the funded account does over its first six months (126 trading days): payouts on average, money to the trader after the split, how soon the first payout comes, how many funded accounts are lost, and what one attempt is worth counting those payouts. Each payout follows the account's rules; after a payout the profit comes out and the account carries on from its starting balance. Give trades with starting_balance, or the four headline numbers.

    Annotations the server declares

    • title: What a funded account is likely to pay
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • rule_changesChanges PropPassCheck has recorded to prop firms' rules, newest first: targets, loss limits, drawdown type, consistency rules, payouts, splits and prices, with the old and new valu…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Changes PropPassCheck has recorded to prop firms' rules, newest first: targets, loss limits, drawdown type, consistency rules, payouts, splits and prices, with the old and new value and whether the change is better or worse for traders. Filter by firm.

    Annotations the server declares

    • title: Recent prop firm rule changes
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • sample_tradersEleven sample traders (breakout, trend following, mean reversion, scalping, swing trading, opening range breakout, day trading, high win rate, low win rate, position trading, and a…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Eleven sample traders (breakout, trend following, mean reversion, scalping, swing trading, opening range breakout, day trading, high win rate, low win rate, position trading, and a grid sample with no edge) replayed 1,000 times against each account's rules: pass and first-payout chance, best risk per trade, typical days and the usual reason for failing. Give id for every style on one account, or style for the accounts where that style does best. They show how rules treat a style, not anyone's own odds.

    Annotations the server declares

    • title: How typical trading styles do on an account
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • test_statsFor a trader with no trade list: estimates the chance of passing, the chance of a first payout and the likely fees per payout from a win rate, reward-to-risk, risk per trade and tr…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    For a trader with no trade list: estimates the chance of passing, the chance of a first payout and the likely fees per payout from a win rate, reward-to-risk, risk per trade and trades per day. It treats every win and every loss as the same size and every day as alike, so it is rougher than a test of real trades and usually a little optimistic.

    Annotations the server declares

    • title: Test a strategy from its headline numbers
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • test_tradesReplays a list of closed trades 1,000 times against prop firm challenge rules and returns, per account: the chance of passing, the chance of reaching a first payout, the usual numb…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Replays a list of closed trades 1,000 times against prop firm challenge rules and returns, per account: the chance of passing, the chance of reaching a first payout, the usual number of trading days, why failed attempts failed, the average number of attempts, and the likely fees per first payout with the funded profit needed to win them back. Give every closed trade's profit or loss in money and the starting balance of the test. Include each trade's close date when known, so busy and quiet days are kept as they happened. Name up to 10 challenge ids, or a firm, or leave both out to rank every account. Needs real closed trades, not figures made up from a win rate.

    Annotations the server declares

    • title: Test a trader's own trades against challenge rules
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • track_accountFor a trader on a live account: from the trade history since the account started, how far the balance is above the maximum-loss floor (static or trailing), what is left of today's …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    For a trader on a live account: from the trade history since the account started, how far the balance is above the maximum-loss floor (static or trailing), what is left of today's daily loss limit and the balance to stop at, progress to the profit target or a payout, the consistency rule and the day counts, with a status. Every trade needs a YYYY-MM-DD close date. Closed trades only: open trades also count at most firms, and the firm's own dashboard is what counts.

    Annotations the server declares

    • title: Track a live challenge or funded account
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
Only reads 3Show 3 read-only tools
  • get_challengeFull rules for one account: profit targets, daily and maximum loss, drawdown type, minimum days, time limit, consistency rule, payout terms, trading restrictions on record (news, w…No findings

    Why it is in this group

    • The name "get_challenge" says "get": a word for reading.
    Description, as the server wrote it
    Full rules for one account: profit targets, daily and maximum loss, drawdown type, minimum days, time limit, consistency rule, payout terms, trading restrictions on record (news, weekends, open losses, short trades), price, the firm's source page, the date checked, recent rule changes and any proof-checked payout reports for the firm. Takes a PropPassCheck account id.

    Annotations the server declares

    • title: Get one challenge's rules
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • list_challengesLists the prop firm accounts PropPassCheck tracks (evaluation challenges and instant funding), each with its id, targets, loss limits, price and the date the rules were last checke…No findings

    Why it is in this group

    • The name "list_challenges" says "list": a word for reading.
    Description, as the server wrote it
    Lists the prop firm accounts PropPassCheck tracks (evaluation challenges and instant funding), each with its id, targets, loss limits, price and the date the rules were last checked. Filter by firm, account type, market, drawdown type, price and the rules a trading style needs (no daily loss limit, no consistency rule, weekend holding, news trading).

    Annotations the server declares

    • title: Find prop firm challenges
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • price_historyList prices with the date tracking began, the lowest list price in the last 30 days and every price change the firm made.No findings

    Why it is in this group

    • The description's first verb is "list": a word for reading.
    Description, as the server wrote it
    List prices with the date tracking began, the lowest list price in the last 30 days and every price change the firm made. Name challenge ids or a firm, or leave both out for every account whose list price changed in the last 90 days. List prices only: PropPassCheck does not track discount codes or use affiliate links.

    Annotations the server declares

    • title: Prop firm list prices and price changes
    • readOnlyHint: true
    • destructiveHint: false
    • 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 or outbound.

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 out0
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 21, 2026, 19:20 UTC, unchanged since Nov 14, 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
10
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 10 tools that change things (10 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://proppasscheck.com/mcp: tools/list returned 13 tools to an anonymous client, including compare_challenges (write), rule_changes (write), test_trades (write), test_stats (write), find_best_size (write) and 5 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

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

    Matched text

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

    What this check looks for
  • The server marks "find_best_size" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "find_best_size" says "find": a word for reading.

    What this check looks for

History

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

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 3.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http prop-firm-tools https://proppasscheck.com/mcp
claude mcp add --transport http prop-firm-tools https://proppasscheck.com/mcp

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__prop-firm-tools__list_challenges",
      "mcp__prop-firm-tools__get_challenge",
      "mcp__prop-firm-tools__price_history"
    ],
    "ask": [
      "mcp__prop-firm-tools__compare_challenges",
      "mcp__prop-firm-tools__rule_changes",
      "mcp__prop-firm-tools__test_trades",
      "mcp__prop-firm-tools__test_stats",
      "mcp__prop-firm-tools__find_best_size",
      "mcp__prop-firm-tools__check_overlap",
      "mcp__prop-firm-tools__funded_life",
      "mcp__prop-firm-tools__fix_strategy",
      "mcp__prop-firm-tools__sample_traders",
      "mcp__prop-firm-tools__track_account"
    ],
    "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 prop-firm-tools. Review it before you use it.

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.proppasscheck/prop-firm-tools/verify?hash=015c511e57ad91dd805997843d894f75a112d5ab2184b1c777c7c7ef94498b79" | jq -e '.changed == false'

Pinned hash 015c511e57ad, from Nov 14, 2026, 08:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.proppasscheck/prop-firm-tools/changes.xml

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

Badge

Anlyon Radar badge for com.proppasscheck/prop-firm-tools
[![Anlyon Radar](https://radar.anlyon.com/badge/com.proppasscheck/prop-firm-tools.svg)](https://radar.anlyon.com/servers/com.proppasscheck/prop-firm-tools)

Source: MCP Registry. Synced Nov 14, 2026, 08:17 UTC.

PropPassCheck MCP server: questions and answers

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

Is the PropPassCheck MCP server safe?

No scan can promise that. What its definitions show: 13 tools, 10 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 PropPassCheck MCP server delete data?

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

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

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the PropPassCheck MCP server have?

13 tools: 10 write, 3 read. compare_challenges, rule_changes, test_trades, test_stats, find_best_size, check_overlap, funded_life, fix_strategy and 5 more.

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

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

Does the PropPassCheck MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the PropPassCheck MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.