mcp-gateway
xyz.trusteed/mcp-gatewaytrusteed.xyzstreamable-httpv1.1.0Scanned
Agentic commerce gateway: discovery, trust and checkout. Demo store; x402 sandbox, AP2 planned.
12 tools: 1 change things and 11 only read.
- Reads private data · 2
- Reads text others write · 11
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
Anlyon alternative
1 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the mcp-gateway can do
The mcp-gateway is published by trusteed.xyz, a domain the MCP Registry verified. It has 12 tools. It can create or change data (1 tool: create_sandbox_key), but cannot delete data. 11 tools only read.
2 tools read private data (search_docs and compare_products); 11 tools bring in text other people can write (search_products_enriched, search_products, get_product_details and 8 more).
The fixed checks matched 1 finding (credentials-mention). 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 19, 2026, version 1.1.0.
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.
12 tools
Changes things 1Claude Code: ask
create_sandbox_keyGet a temporary sandbox credential for this demo store, valid 24h.1 finding
Why it is in this group
- The name "create_sandbox_key" says "create": a word for a change.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "Get a temporary sandbox credential for this demo store, valid 24h. Present..."
Description, as the server wrote it Get a temporary sandbox credential for this demo store, valid 24h. Present it as an `Authorization: Bearer` header, or — when your client cannot set headers — as the `agent_key` argument of the checkout tools. Payments here are simulated: this credential settles nothing and works only on the demo store. No human login is involved at any point.
Only reads 11Show 11 read-only tools
browse_categoriesList all product categories in Demo Store with product counts.Reads text others writeNo findings
Why it is in this group
- The name "browse_categories" says "browse": 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 name "browse_categories" says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it List all product categories in Demo Store with product counts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
compare_productsCompare 2 to 5 products side-by-side with normalized attribute table and best-value recommendation.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "compare_products" says "compare": a word for reading.
What it can reach
- private-dataThe description's first sentence says "compare" and "table": it reads databases.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Compare 2 to 5 products side-by-side with normalized attribute table and best-value recommendation.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_merchant_profileGet the complete profile — trust score, policies, compliance, and protocol support — of the merchant this MCP endpoint belongs to.Reads text others writeNo findings
Why it is in this group
- The name "get_merchant_profile" 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 Get the complete profile — trust score, policies, compliance, and protocol support — of the merchant this MCP endpoint belongs to. Takes NO parameters: the merchant is fixed by which store's /:storeSlug/mcp endpoint you connected to, not by an argument. To read a different merchant's profile, call this same tool on that merchant's own endpoint instead.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_page_contentGet a SUMMARY of a specific page on Trusteed: its title, description, keywords, related tools and the link to the full page.Reads text others writeNo findings
Why it is in this group
- The name "get_page_content" 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 Get a SUMMARY of a specific page on Trusteed: its title, description, keywords, related tools and the link to the full page. It returns a summary, not the full page text: read the linked URL when the whole page is needed. `content_scope` says what came back. Pass the page slug (e.g. 'for-agents', 'pricing', 'blog') or a blog post slug (returns its excerpt). Use get_site_map first to discover available slugs. Pass page='blog' to list all blog posts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_payment_methodsList the payment rails Demo Store really accepts (e.g.Reads text others writeNo findings
Why it is in this group
- The name "get_payment_methods" 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 List the payment rails Demo Store really accepts (e.g. stripe, x402), with the instruments available per rail (card, apple_pay, usdc_base, ...). Derived from the merchant's live connection state — call this BEFORE checkout to negotiate a rail the agent can settle.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_product_detailsGet detailed information about a specific product in Demo Store, including all variants, sizes, colors, and availability.Reads text others writeNo findings
Why it is in this group
- The name "get_product_details" 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 Get detailed information about a specific product in Demo Store, including all variants, sizes, colors, and availability.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_site_mapReturns the complete site map of Trusteed: all public pages organized by category.Reads text others writeNo findings
Why it is in this group
- The name "get_site_map" 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 Returns the complete site map of Trusteed: all public pages organized by category. Use this to discover what sections are available (docs, blog, integrations, legal, marketing) and find the right path before calling get_page_content.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_store_trustGet Demo Store's signed trust score (v4.1, 0-100) with per-signal data quality, confidence level, and a detached JWS for offline verification.Reads text others writeNo findings
Why it is in this group
- The name "get_store_trust" 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 Get Demo Store's signed trust score (v4.1, 0-100) with per-signal data quality, confidence level, and a detached JWS for offline verification. Don't trust the number — verify it: download the JWKS at jwks_snapshot_uri, validate jws_compact with signing_kid, and recompute payload_hash_sha256.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
search_docsFull-text search across all Trusteed public documentation: pages, blog posts, FAQ entries, error codes, the agent checkout guide, and the tools of this endpoint.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "search_docs" says "search": a word for reading.
What it can reach
- private-dataThe name "search_docs" says "search" and "doc": it reads documents.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
Description, as the server wrote it Full-text search across all Trusteed public documentation: pages, blog posts, FAQ entries, error codes, the agent checkout guide, and the tools of this endpoint. Returns ranked results by relevance. Use this to find answers about protocols, pricing, integration guides, trust scores, and more.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
search_productsSearch products in Demo Store.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 products in Demo Store. Returns matching products with prices, images, availability, and direct links. Results include data for generating a visual product carousel artifact with category filtering.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
search_products_enrichedSearch products with enriched data including structured attributes, variants, GTIN, and images.Reads text others writeNo findings
Why it is in this group
- The name "search_products_enriched" 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 products with enriched data including structured attributes, variants, GTIN, and images. Ideal for comparison and detailed product discovery. Matching is keyword/substring-based (title, description, tags, vendor) with rating-then-review ordering — the rating and review count it orders by are asserted by the merchant and are not verified by Trusteed. Use this when you have concrete keywords, a category, or a price range.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- 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 outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write11
- 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.
Looked at Nov 20, 2026, 19:21 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
- 1
- 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.trusteed.xyz/.well-known/oauth-protected-resource/demo-store/mcp/discovery
- 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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.trusteed.xyz/demo-store/mcp/discovery: tools/list returned 12 tools to an anonymous client, including create_sandbox_key (write)
Posture changes
- Nov 20, 2026
- HTTP status of an anonymous initialize: 410 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 1
- Protocol version: none to 2025-06-18
- RFC 9728 protected resource metadata: https://trusteed.xyz/.well-known/oauth-protected-resource/demo-store/mcp to https://api.trusteed.xyz/.well-known/oauth-protected-resource/demo-store/mcp/discovery
- Oct 29, 2026
- HTTP status of an anonymous initialize: 200 to 410
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 14 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
The description mentions "credential".
What this check looks forMatched text
description: "Get a temporary sandbox credential for this demo store, valid 24h. Present..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 410 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 1 (and 2 more).View diff
- HTTP status of an anonymous initialize: 410 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 1
- Protocol version: none to 2025-06-18
- RFC 9728 protected resource metadata: https://trusteed.xyz/.well-known/oauth-protected-resource/demo-store/mcp to https://api.trusteed.xyz/.well-known/oauth-protected-resource/demo-store/mcp/discovery
Tools1 added, 16 removed, 1 changed.+1 added−16 removed~1 changedView diff
- Added:get_payment_methodsOnly reads
- Removed:apply_discount
- Removed:complete_checkout
- Removed:create_cart
- Removed:get_checkout_state
- Removed:get_shipping_rates
- Removed:get_trust_receipt
- Removed:preview_checkout
- Removed:quote_checkout
- Removed:select_shipping_option
- Removed:ucp_cancel_checkout
- Removed:ucp_complete_checkout
- Removed:ucp_create_checkout
- Removed:ucp_get_checkout
- Removed:ucp_preview_checkout
- Removed:ucp_update_checkout
- Removed:verify_trust_receipt
- Changed:get_store_trustOnly readsinputSchema
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 410; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 14 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 410
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 14 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http gateway https://api.trusteed.xyz/demo-store/mcp/discoveryclaude mcp add --transport http gateway https://api.trusteed.xyz/demo-store/mcp/discoveryRun 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.
{
"permissions": {
"allow": [
"mcp__gateway__search_products_enriched",
"mcp__gateway__search_products",
"mcp__gateway__get_product_details",
"mcp__gateway__browse_categories",
"mcp__gateway__get_merchant_profile",
"mcp__gateway__get_site_map",
"mcp__gateway__get_page_content",
"mcp__gateway__search_docs",
"mcp__gateway__compare_products",
"mcp__gateway__get_payment_methods",
"mcp__gateway__get_store_trust"
],
"ask": [
"mcp__gateway__create_sandbox_key"
],
"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 gateway. Review it before you use it.
Capability tags behind 11 rules
- mcp__gateway__search_products_enriched untrusted-input
- mcp__gateway__search_products untrusted-input
- mcp__gateway__get_product_details untrusted-input
- mcp__gateway__browse_categories untrusted-input
- mcp__gateway__get_merchant_profile untrusted-input
- mcp__gateway__get_site_map untrusted-input
- mcp__gateway__get_page_content untrusted-input
- mcp__gateway__search_docs private-data, untrusted-input
- mcp__gateway__compare_products private-data, untrusted-input
- mcp__gateway__get_payment_methods untrusted-input
- mcp__gateway__get_store_trust 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/xyz.trusteed/mcp-gateway/verify?hash=1a5e5ddb8ebec40b280976240b02799cb4724abcc59a6d787da956865525786b" | jq -e '.changed == false'Pinned hash 1a5e5ddb8ebe, from Nov 19, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/xyz.trusteed/mcp-gateway/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/xyz.trusteed/mcp-gateway)Source: MCP Registry · repository. Synced Nov 19, 2026, 20:18 UTC.
mcp-gateway: questions and answers
Answered from the scan above, not from the publisher's description.
Is the mcp-gateway safe?
- No scan can promise that. What its definitions show: 12 tools, 1 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 mcp-gateway delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the mcp-gateway 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 mcp-gateway have?
- 12 tools: 1 write, 11 read. create_sandbox_key, search_products_enriched, search_products, get_product_details, browse_categories, get_merchant_profile, get_site_map, get_page_content and 4 more.
Does the mcp-gateway need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the mcp-gateway send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the mcp-gateway changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.