Skip to content

iPayX FX Audit MCP server

io.github.iPAYX-Technologies/mcp-fx-auditiPAYX-Technologiesstreamable-httpv1.4.0Scanned

Forensic FX audit MCP. Live mid-market rates, spread scoring and hidden bank fee detection.

4 tools: 2 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 2 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 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 iPayX FX Audit MCP server can do

The iPayX FX Audit MCP server is published by the GitHub account iPAYX-Technologies. It has 4 tools. It can create or change data (2 tools: audit_fx_transaction and full_forensic_fx_report), but cannot delete data. 2 tools only read.

4 tools bring in text other people can write (check_fx_mid_market_rate, audit_fx_transaction, full_forensic_fx_report and 1 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

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

Last scanned Nov 20, 2026, version 1.4.0.

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.

4 tools

Changes things 2Claude Code: ask
  • audit_fx_transactionAudits one currency transaction against the live mid-market rate.Reads text others writeNo 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Audits one currency transaction against the live mid-market rate. Inputs: amount, currency_from, currency_to, bank_rate. Output: FX score from 1 to 10, rating, color badge, verdict, currency pair, amount and date.

    Annotations the server declares

    • title: Audit FX Transaction
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • full_forensic_fx_reportProduces a full FX audit report for one transaction (score, spread, estimated loss, breakdown and routing recommendation).Reads text others writeNo 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Produces a full FX audit report for one transaction (score, spread, estimated loss, breakdown and routing recommendation). Inputs: amount, currency_from, currency_to, bank_rate, optional company_name. Requires a Bearer API key from https://www.ipayx.ai/ai-access.

    Annotations the server declares

    • title: Full Forensic FX Report
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 2Show 2 read-only tools
  • check_fx_mid_market_rateReturns the live mid-market FX rate for a currency pair (Twelve Data, Open Exchange Rates fallback), in both directions (pair and inverted_pair).Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Returns the live mid-market FX rate for a currency pair (Twelve Data, Open Exchange Rates fallback), in both directions (pair and inverted_pair). Inputs: currency_from, currency_to, optional bank_rate. When bank_rate is given, the output also includes the spread versus mid-market; both quote directions (rate and 1/rate) are tested, the closer one is kept and flagged as inverted when 1/rate wins; a rate more than 10% from mid-market in both directions is rejected as incoherent.

    Annotations the server declares

    • title: Check FX Mid-Market Rate
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • compare_fx_sourcesCompares FX rates side by side: live mid-market, the Stripe FX Quotes API (when stripe_api_key is given) and the bank rate.Reads text others writeNo findings

    Why it is in this group

    • The name "compare_fx_sources" says "compare": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Compares FX rates side by side: live mid-market, the Stripe FX Quotes API (when stripe_api_key is given) and the bank rate. Inputs: amount, currency_from, currency_to, bank_rate, optional bank_name and stripe_api_key. Output: each source's effective rate, markup in basis points, cost per 100,000, FX score, and the lowest-cost source.

    Annotations the server declares

    • title: Compare FX Sources (Bank vs Stripe vs Mid-Market)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true

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 outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
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 20, 2026, 19:05 UTC, unchanged since Nov 20, 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
2
Protocol version
2025-03-26
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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.ipayx.ai/mcp: tools/list returned 4 tools to an anonymous client, including audit_fx_transaction (write), full_forensic_fx_report (write)

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • Legacy HTTP+SSE transport: yes to no

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

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

  1. PostureRemote posture changed. Legacy HTTP+SSE transport: yes -> no.View diff
    • Legacy HTTP+SSE transport: yes to no
  2. Tools4 changed.~4 changedView diff

Install

Pinned to version 1.4.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http fx-audit https://mcp.ipayx.ai/mcp
claude mcp add --transport http fx-audit https://mcp.ipayx.ai/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__fx-audit__check_fx_mid_market_rate",
      "mcp__fx-audit__compare_fx_sources"
    ],
    "ask": [
      "mcp__fx-audit__audit_fx_transaction",
      "mcp__fx-audit__full_forensic_fx_report"
    ],
    "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 fx-audit. Review it before you use it.

Capability tags behind 4 rules
  • mcp__fx-audit__check_fx_mid_market_rate untrusted-input
  • mcp__fx-audit__audit_fx_transaction untrusted-input
  • mcp__fx-audit__full_forensic_fx_report untrusted-input
  • mcp__fx-audit__compare_fx_sources untrusted-input

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/io.github.iPAYX-Technologies/mcp-fx-audit/verify?hash=32001958b41e1f321a148c7aa5f5707caaba67028c05cbfc88f45dae71fbe119" | jq -e '.changed == false'

Pinned hash 32001958b41e, from Nov 20, 2026, 18:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.iPAYX-Technologies/mcp-fx-audit/changes.xml

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

Badge

Anlyon Radar badge for io.github.iPAYX-Technologies/mcp-fx-audit
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.iPAYX-Technologies/mcp-fx-audit.svg)](https://radar.anlyon.com/servers/io.github.iPAYX-Technologies/mcp-fx-audit)

Source: MCP Registry · repository. Synced Nov 20, 2026, 18:18 UTC.

iPayX FX Audit MCP server: questions and answers

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

Is the iPayX FX Audit MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 2 of which can change, send or delete something, and 0 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 iPayX FX Audit MCP server delete data?

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

Can the iPayX FX Audit 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 iPayX FX Audit MCP server have?

4 tools: 2 write, 2 read. audit_fx_transaction, full_forensic_fx_report, check_fx_mid_market_rate and compare_fx_sources.

Does the iPayX FX Audit MCP server need sign-in or OAuth?

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

Does the iPayX FX Audit MCP server send data to outside services?

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

Has the iPayX FX Audit MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.