Skip to content

BuyWise MCP server

fyi.buywise/buywisebuywise.fyistreamable-httpv1.1.2Scanned

Know what you're buying: brand, white-label, price, fake-discount, review and seller checks

3 tools: 3 change things.

Tools: 0 delete, 0 irreversible, 3 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

3 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 BuyWise MCP server can do

The BuyWise MCP server is published by buywise.fyi, a domain the MCP Registry verified. It has 3 tools. It can create or change data (3 tools: check_brands, check_product and check_products), but cannot delete data. None of its tools only reads.

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

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.

Last scanned Nov 15, 2026, version 1.1.2.

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.

3 tools

Changes things 3Claude Code: ask
  • check_brandsUse this when the user asks whether a brand is reputable or what kind of brand it is (an established name, a store's own label, an independent maker, or a generic white-label name)…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
    Use this when the user asks whether a brand is reputable or what kind of brand it is (an established name, a store's own label, an independent maker, or a generic white-label name), or wants brands compared while shopping. Returns findings on each brand: what kind of brand it is, its reputation for quality and its usual price tier, each with a confidence. Signals only, never a buy or avoid verdict. Does not browse the web and is not for banking, health or email pages. Pass brand names as the user or the listing gave them, up to 50 per call.

    Annotations the server declares

    • title: Check brands
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • check_productUse this when the user is looking at a specific product listing on an online store and wants to know whether it looks trustworthy or like a good buy.Can send data outNo 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

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Use this when the user is looking at a specific product listing on an online store and wants to know whether it looks trustworthy or like a good buy. Pass what you already read from the listing as arguments: title (required) and, when shown, brand, price, listPrice (the seller's "was" price), currency, url, seller, category, rating, reviewCount and key details; each extra field sharpens the read. Returns findings such as generic white-label product, quality, price, questionable discount, review credibility and seller legitimacy, each with a confidence, plus a report on the brand unless includeBrand is false. Signals only, never a buy or avoid verdict. Does not browse: only the domain of url is used. Not for banking, health, government or email pages.

    Annotations the server declares

    • title: Check a product listing
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • check_productsUse this when the user is comparing several product listings, such as search results or the same item at different stores, and wants trust signals on each.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
    Use this when the user is comparing several product listings, such as search results or the same item at different stores, and wants trust signals on each. Pass up to 20 products, each with what you already read from its listing: title (required) and, when shown, brand, price, listPrice, currency, url, seller, category, rating, reviewCount, details, plus your own id to match results. Returns, in input order, the same findings as check_product for each; a product that can't be checked carries an error and message instead. Signals only, never a buy or avoid verdict. Does not browse the web. Not for banking, health, government or email pages.

    Annotations the server declares

    • title: Check product listings
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: 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, 18:54 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
https://api.buywise.fyi/.well-known/oauth-protected-resource/mcp
Authorization servers
https://api.buywise.fyi
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
yes
  • WarnThe whole server

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

    Matched text

    https://api.buywise.fyi/mcp: tools/list returned 3 tools to an anonymous client, including check_brands (write), check_product (write), check_products (write)

    What this check looks for

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.

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

Install

Pinned to version 1.1.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http buywise https://api.buywise.fyi/mcp
claude mcp add --transport http buywise https://api.buywise.fyi/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": [],
    "ask": [
      "mcp__buywise__check_brands",
      "mcp__buywise__check_product",
      "mcp__buywise__check_products"
    ],
    "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 buywise. Review it before you use it.

Capability tags behind 1 rule
  • mcp__buywise__check_product 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/fyi.buywise/buywise/verify?hash=b10bb6c825c23c78e88d58bff9a464fde6e9cf3a374f0d680a716c00ca4dff05" | jq -e '.changed == false'

Pinned hash b10bb6c825c2, from Nov 15, 2026, 10:17 UTC.

Watch

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

https://radar.anlyon.com/servers/fyi.buywise/buywise/changes.xml

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

Badge

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

Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.

BuyWise MCP server: questions and answers

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

Is the BuyWise MCP server safe?

No scan can promise that. What its definitions show: 3 tools, 3 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 BuyWise MCP server delete data?

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

Can the BuyWise 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 BuyWise MCP server have?

3 tools: 3 write. check_brands, check_product and check_products.

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

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

Does the BuyWise 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): check_product.

Has the BuyWise MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.