Skip to content

AgentRoam MCP server

ai.agentroam/agentroamagentroam.aistreamable-httpv1.0.0Scanned

Buy travel eSIMs, gift cards and mobile top-ups with crypto — user confirms before any order.

11 tools: 2 can delete or cancel things, 1 change things and 8 only read.

Tools: 2 delete, 0 irreversible, 1 write, 8 read.
  • Reads private data · 0
  • Reads text others write · 9
  • Can send data out · 1
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here can delete or cancel 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 AgentRoam MCP server can do

The AgentRoam MCP server is published by agentroam.ai, a domain the MCP Registry verified. It has 11 tools. It can delete or cancel things (2 tools: create_order and purchase_wizard) and create or change data (1 tool: validate_order). 8 tools only read.

9 tools bring in text other people can write (search_products, get_price, validate_order and 6 more); 1 tool can send data out of your system (validate_order).

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

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.

11 tools

Deletes or cancels 2Claude Code: deny
  • create_orderCreates the real order.Reads text others writeNo findings

    Why it is in this group

    • The name "create_order" says "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    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
    Creates the real order. Requires a confirm_token minted by validate_order. Returns the payment wallet address, exact crypto amount, 30-minute expiry, and an order-status URL. The purchased code/QR is emailed by Cryptorefills to the buyer — it is never returned here.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: true
    • destructiveHint: true
    • title: Place order
  • purchase_wizardStateful text-only purchase flow for clients without widget support.Reads text others writeNo findings

    Why it is in this group

    • The name "purchase_wizard" says "purchase": a word that usually means money moves, which cannot be taken back.
    • The server marks it destructive (destructiveHint: true).

    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
    Stateful text-only purchase flow for clients without widget support. Called repeatedly with the same session_token, one question at a time, until status is "complete"; the first call takes empty arguments. The final "confirm" answer creates a real order.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: true
    • destructiveHint: true
    • title: Guided purchase (text)
Changes things 1Claude Code: ask
  • validate_orderDry-run an order and mint a one-time confirm_token (valid 10 minutes).Reads text others writeCan send data out1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a destination (input.phone): what the tool writes goes there.

    Findings

    • Warn

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

      Matched text

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

      What this check looks for
    Description, as the server wrote it
    Dry-run an order and mint a one-time confirm_token (valid 10 minutes). Returns a human-readable purchase summary for the buyer to approve, plus the one-time token that create_order requires. Creates no order and reserves no funds.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: true
    • destructiveHint: false
    • title: Prepare order for approval
Only reads 8Show 8 read-only tools
  • get_currenciesList all supported payment cryptocurrencies (the response carries the current set).No findings

    Why it is in this group

    • The name "get_currencies" says "get": a word for reading.
    Description, as the server wrote it
    List all supported payment cryptocurrencies (the response carries the current set).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
    • title: List payment coins
  • get_order_statusPoll order state (WAITING_FOR_PAYMENT → PARTIAL → COMPLETED, or CANCELED/EXPIRED).Reads text others writeNo findings

    Why it is in this group

    • The name "get_order_status" says "get": 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
    Poll order state (WAITING_FOR_PAYMENT → PARTIAL → COMPLETED, or CANCELED/EXPIRED). Requires the status_token from create_order.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • title: Check order status
  • get_payment_methodsFull payment matrix: every supported coin × network combination currently available, with the exact network strings orders require.No findings

    Why it is in this group

    • The name "get_payment_methods" says "get": a word for reading.
    Description, as the server wrote it
    Full payment matrix: every supported coin × network combination currently available, with the exact network strings orders require. The response includes live totals for coins, networks and combinations.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
    • title: List payment networks
  • get_priceLive crypto price for one product/denomination.Reads text others writeNo findings

    Why it is in this group

    • The name "get_price" says "get": 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
    Live crypto price for one product/denomination. Payment coins include USDT, USDC, BTC (incl. Lightning), ETH, SOL, DAI, PYUSD, LTC, TRX, TON, DOGE and SUI across many networks; get_payment_methods returns the current set. Creates no order.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • title: Get crypto price
  • list_brandsBrowse all available brands/carriers for a country: gift cards (500+ US brands) and mobile top-up carriers (100+ countries).Reads text others writeNo findings

    Why it is in this group

    • The name "list_brands" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Browse all available brands/carriers for a country: gift cards (500+ US brands) and mobile top-up carriers (100+ countries). Creates no order.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • title: List brands by country
  • list_esim_plansLive eSIM data plans for a destination (110+ countries, plus "eu" Europe and "ww" Global multi-country plans) with USD prices and crypto amounts.Reads text others writeNo findings

    Why it is in this group

    • The name "list_esim_plans" says "list": 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
    Live eSIM data plans for a destination (110+ countries, plus "eu" Europe and "ww" Global multi-country plans) with USD prices and crypto amounts. In clients that support widgets, the response also renders an interactive plan picker. Creates no order by itself.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • title: List eSIM plans
  • list_productsList a brand's live products/denominations with prices in the chosen coin — including the exact denomination labels the pricing and order tools expect (eSIM destinations are covere…Reads text others writeNo findings

    Why it is in this group

    • The name "list_products" says "list": 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
    List a brand's live products/denominations with prices in the chosen coin — including the exact denomination labels the pricing and order tools expect (eSIM destinations are covered by list_esim_plans). Creates no order.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • title: List brand products
  • search_productsSearch the AgentRoam travel-crypto catalog: gift cards (Airbnb, Uber, airlines, 500+ US brands), eSIM data plans (110+ destinations incl.Reads text others writeNo findings

    Why it is in this group

    • The name "search_products" says "search": 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
    Search the AgentRoam travel-crypto catalog: gift cards (Airbnb, Uber, airlines, 500+ US brands), eSIM data plans (110+ destinations incl. Europe/Global region plans) and mobile top-ups (carriers in 100+ countries). Returns product handles (brandSlug + countryCode) used by the pricing and order tools. Creates no order.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • title: Search catalog

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.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write9
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, 18:24 UTC, unchanged since Oct 22, 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
3
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (2 destructive, 1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agentroam.ai/api/mcp: tools/list returned 11 tools to an anonymous client, including create_order (destructive), purchase_wizard (destructive), validate_order (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

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

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "validate_order" says "validate": 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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentroam https://agentroam.ai/api/mcp
claude mcp add --transport http agentroam https://agentroam.ai/api/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__agentroam__search_products",
      "mcp__agentroam__get_price",
      "mcp__agentroam__list_esim_plans",
      "mcp__agentroam__get_order_status",
      "mcp__agentroam__list_brands",
      "mcp__agentroam__list_products",
      "mcp__agentroam__get_currencies",
      "mcp__agentroam__get_payment_methods"
    ],
    "ask": [
      "mcp__agentroam__validate_order"
    ],
    "deny": [
      "mcp__agentroam__create_order",
      "mcp__agentroam__purchase_wizard"
    ]
  }
}

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 agentroam. Review it before you use it.

Capability tags behind 9 rules
  • mcp__agentroam__search_products untrusted-input
  • mcp__agentroam__get_price untrusted-input
  • mcp__agentroam__validate_order untrusted-input, outbound
  • mcp__agentroam__create_order untrusted-input
  • mcp__agentroam__list_esim_plans untrusted-input
  • mcp__agentroam__get_order_status untrusted-input
  • mcp__agentroam__list_brands untrusted-input
  • mcp__agentroam__list_products untrusted-input
  • mcp__agentroam__purchase_wizard 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/ai.agentroam/agentroam/verify?hash=1f11119ea1e4608730e7035f778988d944d30b2c2d7c6e9e626de25adb0aa020" | jq -e '.changed == false'

Pinned hash 1f11119ea1e4, from Nov 10, 2026, 01:17 UTC.

Watch

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

https://radar.anlyon.com/servers/ai.agentroam/agentroam/changes.xml

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

Badge

Anlyon Radar badge for ai.agentroam/agentroam
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.agentroam/agentroam.svg)](https://radar.anlyon.com/servers/ai.agentroam/agentroam)

Source: MCP Registry · repository. Synced Oct 21, 2026, 17:41 UTC.

AgentRoam MCP server: questions and answers

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

Is the AgentRoam MCP server safe?

No scan can promise that. What its definitions show: 11 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the AgentRoam MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: create_order and purchase_wizard.

Can the AgentRoam 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 AgentRoam MCP server have?

11 tools: 2 destructive, 1 write, 8 read. create_order, purchase_wizard, validate_order, search_products, get_price, list_esim_plans, get_order_status, list_brands and 3 more.

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

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

Does the AgentRoam 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): validate_order.

Has the AgentRoam MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.