Seller Toolbelt MCP server
com.sellertoolbelt/mcpsellertoolbelt.comstreamable-httpv1.0.0Scanned
Check and fix Amazon, eBay and Etsy product images, calculate marketplace fees, look up barcodes.
11 tools: 3 can delete or cancel things, 7 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 8
- Can send data out · 0
- 5 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 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.
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 Seller Toolbelt MCP server can do
The Seller Toolbelt MCP server is published by sellertoolbelt.com, a domain the MCP Registry verified. It has 11 tools. It can delete or cancel things (3 tools: make_compliant_main_image, remove_background and change_background_color) and create or change data (7 tools: check_listing_image, calculate_marketplace_fees, lookup_barcode, generate_qr_code and 3 more). 1 tool only reads.
8 tools bring in text other people can write (check_listing_image, lookup_barcode, make_compliant_main_image and 5 more).
The fixed checks matched 5 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 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 3Claude Code: deny
change_background_colorRemoves the background and places the product on a solid colour: white, light_gray, gray, black, beige, studio_blue, soft_pink, or custom with hex.Reads text others write1 finding
Why it is in this group
- The description's first verb is "remove": a word for removing or ending something.
- The server marks it not destructive (destructiveHint: false), 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.
Findings
- Warn
The server marks "change_background_color" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "remove": a word for removing or ending something.
Description, as the server wrote it Removes the background and places the product on a solid colour: white, light_gray, gray, black, beige, studio_blue, soft_pink, or custom with hex. Without an API key: returns a free watermarked preview (≤700px) plus unlock_url, which a human opens to download the full-resolution file for site credits (then call get_result). With an API key (Authorization: Bearer stb_…): returns download_url for the full-resolution file directly and charges the key owner's credits when the job starts, refunded automatically if processing fails. Retrying a call creates and charges a new job — use get_result to fetch an earlier one.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
make_compliant_main_imageRemoves the background, centres and scales the product on pure white, sizes and encodes it to the marketplace spec (Amazon, eBay or Etsy), then re-checks the result and returns the…Reads text others write1 finding
Why it is in this group
- The description's first verb is "remove": a word for removing or ending something.
- The server marks it not destructive (destructiveHint: false), 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.
Findings
- Warn
The server marks "make_compliant_main_image" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "remove": a word for removing or ending something.
Description, as the server wrote it Removes the background, centres and scales the product on pure white, sizes and encodes it to the marketplace spec (Amazon, eBay or Etsy), then re-checks the result and returns the per-rule verdict as proof. Without an API key: returns a free watermarked preview (≤700px) plus unlock_url, which a human opens to download the full-resolution file for site credits (then call get_result). With an API key (Authorization: Bearer stb_…): returns download_url for the full-resolution file directly and charges the key owner's credits when the job starts, refunded automatically if processing fails. Retrying a call creates and charges a new job — use get_result to fetch an earlier one.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
remove_backgroundCuts the product out of its background and returns a transparent PNG.Reads text others write1 finding
Why it is in this group
- The name "remove_background" says "remove": a word for removing or ending something.
- The server marks it not destructive (destructiveHint: false), 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.
Findings
- Warn
The server marks "remove_background" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "remove_background" says "remove": a word for removing or ending something.
Description, as the server wrote it Cuts the product out of its background and returns a transparent PNG. Without an API key: returns a free watermarked preview (≤700px) plus unlock_url, which a human opens to download the full-resolution file for site credits (then call get_result). With an API key (Authorization: Bearer stb_…): returns download_url for the full-resolution file directly and charges the key owner's credits when the job starts, refunded automatically if processing fails. Retrying a call creates and charges a new job — use get_result to fetch an earlier one.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
Changes things 7Claude Code: ask
add_watermarkStamps text (e.g.Reads text others writeNo findings
Why it is in this group
- The name "add_watermark" says "add": a word for a change.
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 Stamps text (e.g. "© Your Brand") on an image in a corner, the centre, or tiled diagonally. Without an API key: returns a free watermarked preview (≤700px) plus unlock_url, which a human opens to download the full-resolution file for site credits (then call get_result). With an API key (Authorization: Bearer stb_…): returns download_url for the full-resolution file directly and charges the key owner's credits when the job starts, refunded automatically if processing fails. Retrying a call creates and charges a new job — use get_result to fetch an earlier one.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
calculate_marketplace_feesComputes selling fees, net profit, margin and ROI for one sale on Amazon, eBay or Etsy from the sale price, shipping and costs.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 Computes selling fees, net profit, margin and ROI for one sale on Amazon, eBay or Etsy from the sale price, shipping and costs. Category sets the default fee rate: amazon: default (15%), electronics (8%), computers (7%), clothing (17%), home (15%), toys (15%), books (15%); ebay: default (13.25%), electronics (9%), books (14.95%), clothing (13.25%); etsy: default (6.5%). Rates are 2026 estimates and vary by region; pass fee_rate_percent to override. Currency-agnostic. Free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
check_listing_imageDeterministically checks whether a product photo meets the main-image requirements of Amazon, eBay or Etsy (pure white background, product fill, minimum resolution, file format, co…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 Deterministically checks whether a product photo meets the main-image requirements of Amazon, eBay or Etsy (pure white background, product fill, minimum resolution, file format, colour space, borders, aspect ratio, sharpness, stray text/watermarks). Measured from the actual pixels, not guessed by a vision model. Returns pass / warn / fail with a reason per rule. Use before uploading a listing image. Free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
convert_imageRe-encodes an image as jpeg, png, webp, avif at a chosen quality, to change format or shrink file size.Reads text others writeNo findings
Why it is in this group
- The name "convert_image" says "convert": a word for a change.
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 Re-encodes an image as jpeg, png, webp, avif at a chosen quality, to change format or shrink file size. JPEG flattens transparency to white. Without an API key: returns a free watermarked preview (≤700px) plus unlock_url, which a human opens to download the full-resolution file for site credits (then call get_result). With an API key (Authorization: Bearer stb_…): returns download_url for the full-resolution file directly and charges the key owner's credits when the job starts, refunded automatically if processing fails. Retrying a call creates and charges a new job — use get_result to fetch an earlier one.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
generate_qr_codeGenerates a QR code image (PNG) or SVG markup for any text or URL, e.g.1 finding
Why it is in this group
- The name "generate_qr_code" says "generate": 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 "generate_qr_code" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "generate_qr_code" says "generate": a word for a change.
Description, as the server wrote it Generates a QR code image (PNG) or SVG markup for any text or URL, e.g. for packaging inserts, product labels or invoices. Free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
lookup_barcodeFinds product details (title, brand, category, image, description) for a UPC, EAN or GTIN barcode, using open product catalogs (strong for UK/EU groceries, drinks and cosmetics).Reads text others write1 finding
Why it is in this group
- The name "lookup_barcode" says "lookup": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- 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.
Findings
- Warn
The server marks "lookup_barcode" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "lookup_barcode" says "lookup": a word for reading.
Description, as the server wrote it Finds product details (title, brand, category, image, description) for a UPC, EAN or GTIN barcode, using open product catalogs (strong for UK/EU groceries, drinks and cosmetics). Free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
resize_for_marketplaceFits the image onto an exact canvas, padding with white: amazon (2000×2000), ebay (1600×1600), etsy (2000×2000), square (1080×1080), instagram_portrait (1080×1350), story (1080×192…Reads text others writeNo findings
Why it is in this group
- The name "resize_for_marketplace" says "resize": a word for a change.
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 Fits the image onto an exact canvas, padding with white: amazon (2000×2000), ebay (1600×1600), etsy (2000×2000), square (1080×1080), instagram_portrait (1080×1350), story (1080×1920), or custom width/height. Without an API key: returns a free watermarked preview (≤700px) plus unlock_url, which a human opens to download the full-resolution file for site credits (then call get_result). With an API key (Authorization: Bearer stb_…): returns download_url for the full-resolution file directly and charges the key owner's credits when the job starts, refunded automatically if processing fails. Retrying a call creates and charges a new job — use get_result to fetch an earlier one.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
Only reads 1Show 1 read-only tool
get_resultChecks a job created by one of the image tools.No findings
Why it is in this group
- The name "get_result" says "get": a word for reading.
Description, as the server wrote it Checks a job created by one of the image tools. Returns download_url once it is unlocked (API-key jobs are paid up front; anonymous ones by a human via unlock_url). Otherwise returns the status, preview_url and unlock_url. Never charges. Anonymous results expire 24h after creation unless claimed.
Annotations the server declares
- readOnlyHint: 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 outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write8
- 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, 18:46 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
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (3 destructive, 7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://sellertoolbelt.com/api/mcp: tools/list returned 11 tools to an anonymous client, including make_compliant_main_image (destructive), remove_background (destructive), change_background_color (destructive), check_listing_image (write), calculate_marketplace_fees (write) and 5 more
Findings
Matches of fixed checks, with the text they matched.
- Warnlookup_barcode
The server marks "lookup_barcode" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "lookup_barcode" says "lookup": a word for reading.
- Warngenerate_qr_code
The server marks "generate_qr_code" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "generate_qr_code" says "generate": a word for a change.
The server marks "make_compliant_main_image" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "remove": a word for removing or ending something.
The server marks "remove_background" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "remove_background" says "remove": a word for removing or ending something.
The server marks "change_background_color" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "remove": a word for removing or ending something.
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 sellertoolbelt https://sellertoolbelt.com/api/mcpclaude mcp add --transport http sellertoolbelt https://sellertoolbelt.com/api/mcpRun 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__sellertoolbelt__get_result"
],
"ask": [
"mcp__sellertoolbelt__check_listing_image",
"mcp__sellertoolbelt__calculate_marketplace_fees",
"mcp__sellertoolbelt__lookup_barcode",
"mcp__sellertoolbelt__generate_qr_code",
"mcp__sellertoolbelt__resize_for_marketplace",
"mcp__sellertoolbelt__convert_image",
"mcp__sellertoolbelt__add_watermark"
],
"deny": [
"mcp__sellertoolbelt__make_compliant_main_image",
"mcp__sellertoolbelt__remove_background",
"mcp__sellertoolbelt__change_background_color"
]
}
}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 sellertoolbelt. Review it before you use it.
Capability tags behind 8 rules
- mcp__sellertoolbelt__check_listing_image untrusted-input
- mcp__sellertoolbelt__lookup_barcode untrusted-input
- mcp__sellertoolbelt__make_compliant_main_image untrusted-input
- mcp__sellertoolbelt__remove_background untrusted-input
- mcp__sellertoolbelt__change_background_color untrusted-input
- mcp__sellertoolbelt__resize_for_marketplace untrusted-input
- mcp__sellertoolbelt__convert_image untrusted-input
- mcp__sellertoolbelt__add_watermark 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/com.sellertoolbelt/mcp/verify?hash=eb03349e258b5b9418a6a918124bf3fb8e9d81bda2c604c31dd5c28fc42971a9" | jq -e '.changed == false'Pinned hash eb03349e258b, from Nov 14, 2026, 07:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.sellertoolbelt/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.sellertoolbelt/mcp)Source: MCP Registry. Synced Oct 21, 2026, 18:04 UTC.
Seller Toolbelt MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Seller Toolbelt MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 10 of which can change, send or delete something, and 5 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 Seller Toolbelt MCP server delete data?
- Yes. 3 tools can delete, cancel or revoke something: make_compliant_main_image, remove_background and change_background_color.
Can the Seller Toolbelt 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 Seller Toolbelt MCP server have?
- 11 tools: 3 destructive, 7 write, 1 read. make_compliant_main_image, remove_background, change_background_color, check_listing_image, calculate_marketplace_fees, lookup_barcode, generate_qr_code, resize_for_marketplace and 3 more.
Does the Seller Toolbelt MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Seller Toolbelt MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Seller Toolbelt MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.