Ottom
Check how ready an online store is for AI shopping agents, and read public benchmarks.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"ottom": {
"url": "https://ottom.io/mcp"
}
}
}Remote endpoints
https://ottom.io/mcpstreamable-httpWhat it can do
Tool inventory
Tools (3)
🟢check_store_readiness(url)
Runs a light check of one store page, the way an AI shopping agent reads it: robots.txt, llms.txt, the product feed, the UCP manifest, structured data (product, price, availability, GTIN) and whether the price is in text an agent can read. Each finding comes with a plain explanation, a fix and a link to read more. If the store’s owner publishes an Ottom result with the Ottom badge, that result is included too. Pass a product page URL for the most findings; a home page works. Every answer links to a full scan on ottom.io.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 3,
"maxLength": 2048,
"description": "A store page, ideally a product page, e.g. yourstore.com/products/your-product"
}
},
"required": [
"url"
]
}Output Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The page that was checked, as Ottom read the address."
},
"host": {
"type": "string",
"description": "The store’s host name."
},
"publishedResult": {
"anyOf": [
{
"type": "object",
"properties": {
"result": {
"type": "string",
"description": "The stamped result: PASS, SLOW, STALLED, or NOT CHECKED RECENTLY."
},
"score": {
"description": "The store’s Ottom score out of 100, or null.",
"type": [
"number",
"null"
]
},
"checkedAt": {
"description": "When the full scan behind the result ran, as an ISO 8601 time.",
"type": [
"string",
"null"
]
},
"page": {
"type": "string",
"description": "The store’s public result page on ottom.io."
}
},
"required": [
"result",
"score",
"checkedAt",
"page"
],
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "The store’s own Ottom result, only when its owner publishes it with the Ottom badge. Null for every other store."
},
"publishedResultNote": {
"type": "string",
"description": "One sentence saying where the result comes from."
},
"lightCheck": {
"type": "object",
"properties": {
"outcome": {
"type": "string",
"enum": [
"analysed",
"blocked_by_robots",
"rejected",
"unreachable",
"password_protected"
],
"description": "analysed: the page was read. blocked_by_robots: robots.txt asked Ottom not to read it. rejected: the address was refused before any request. unreachable: no page came back. password_protected: the store is behind a storefront password."
},
"reason": {
"description": "Why the page was not read, when it was not.",
"type": [
"string",
"null"
]
},
"fromRecentCheck": {
"type": "boolean",
"description": "True when the answer comes from a check of the same page in the last 30 minutes."
},
"surfaces": {
"type": "object",
"properties": {
"robotsTxt": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The address Ottom asked for."
},
"found": {
"type": "boolean",
"description": "True only when Ottom fetched it and it was there."
},
"checked": {
"type": "boolean",
"description": "False when the request failed or the check ran out of requests. Never a verdict."
},
"detail": {
"description": "A short note on what was found, or null.",
"type": [
"string",
"null"
]
},
"allowsThisPage": {
"type": "boolean",
"description": "Whether robots.txt lets agents read this page."
}
},
"required": [
"url",
"found",
"checked",
"detail",
"allowsThisPage"
],
"additionalProperties": false,
"description": "The store’s robots.txt."
},
"llmsTxt": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The address Ottom asked for."
},
"found": {
"type": "boolean",
"description": "True only when Ottom fetched it and it was there."
},
"checked": {
"type": "boolean",
"description": "False when the request failed or the check ran out of requests. Never a verdict."
},
"detail": {
"description": "A short note on what was found, or null.",
"type": [
"string",
"null"
]
}
},
"required": [
"url",
"found",
"checked",
"detail"
],
"additionalProperties": false,
"description": "The store’s llms.txt."
},
"productFeed": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The address Ottom asked for."
},
"found": {
"type": "boolean",
"description": "True only when Ottom fetched it and it was there."
},
"checked": {
"type": "boolean",
"description": "False when the request failed or the check ran out of requests. Never a verdict."
},
"detail": {
"description": "A short note on what was found, or null.",
"type": [
"string",
"null"
]
},
"productCount": {
"type": "number",
"description": "How many products the feed lists."
}
},
"required": [
"url",
"found",
"checked",
"detail",
"productCount"
],
"additionalProperties": false,
"description": "A machine readable product feed."
},
"ucpManifest": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The address Ottom asked for."
},
"found": {
"type": "boolean",
"description": "True only when Ottom fetched it and it was there."
},
"checked": {
"type": "boolean",
"description": "False when the request failed or the check ran out of requests. Never a verdict."
},
"detail": {
"description": "A short note on what was found, or null.",
"type": [
"string",
"null"
]
},
"valid": {
"type": "boolean",
"description": "Whether the manifest is valid. Meaningful only when found."
},
"version": {
"description": "The manifest’s version, when it has one.",
"type": [
"string",
"null"
]
}
},
"required": [
"url",
"found",
"checked",
"detail",
"valid",
"version"
],
"additionalProperties": false,
"description": "The Universal Commerce Protocol manifest at /.well-known/ucp."
}
},
"required": [
"robotsTxt",
"llmsTxt",
"productFeed",
"ucpManifest"
],
"additionalProperties": false,
"description": "The files an agent reads beside the page."
},
"structuredData": {
"type": "object",
"properties": {
"blocks": {
"type": "number",
"description": "How many JSON-LD blocks the page has."
},
"productFound": {
"type": "boolean",
"description": "Whether schema.org Product markup was found."
},
"priceInMarkup": {
"type": "boolean",
"description": "Whether the markup carries a price."
},
"priceInAgentText": {
"type": "boolean",
"description": "Whether the price is in the text an agent reads, not only in images or scripts."
}
},
"required": [
"blocks",
"productFound",
"priceInMarkup",
"priceInAgentText"
],
"additionalProperties": false,
"description": "What the page’s own markup says about the product."
},
"botWall": {
"type": "boolean",
"description": "Whether a bot wall answered instead of the page."
},
"findings": {
"type": "array",
"items": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The stall code, the same one a full scan reports."
},
"severity": {
"type": "string",
"enum": [
"critical",
"high",
"medium",
"low",
"info"
],
"description": "How much the finding gets in an agent’s way."
},
"stage": {
"type": "string",
"enum": [
"discover",
"evaluate",
"compare",
"buy"
],
"description": "The stage of a purchase the finding affects."
},
"title": {
"type": "string",
"description": "The finding in a few words."
},
"explanation": {
"type": "string",
"description": "What is wrong, in plain words."
},
"fix": {
"type": "string",
"description": "What to change, written to forward to a developer."
},
"learnMore": {
"type": "string",
"description": "A page on ottom.io about this finding."
}
},
"required": [
"code",
"severity",
"stage",
"title",
"explanation",
"fix",
"learnMore"
],
"additionalProperties": false
},
"description": "What would stop or slow an AI agent here. Empty when nothing was found."
},
"notChecked": {
"type": "array",
"items": {
"type": "object",
"properties": {
"label": {
"type": "string",
"description": "What was not checked."
},
"why": {
"type": "string",
"description": "Why not."
}
},
"required": [
"label",
"why"
],
"additionalProperties": false
},
"description": "What the light check did not look at, named so absence never reads as a pass."
}
},
"required": [
"outcome",
"reason",
"fromRecentCheck",
"surfaces",
"structuredData",
"botWall",
"findings",
"notChecked"
],
"additionalProperties": false,
"description": "A light check of the page, run now or in the last 30 minutes."
},
"fullScan": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Where to start a full scan of the store on ottom.io."
},
"note": {
"type": "string",
"description": "What a full scan adds."
}
},
"required": [
"url",
"note"
],
"additionalProperties": false,
"description": "A full scan, in which an AI agent tries to buy."
}
},
"required": [
"url",
"host",
"publishedResult",
"publishedResultNote",
"lightCheck",
"fullScan"
],
"additionalProperties": false
}🟢get_benchmark(category)
Returns Ottom’s published benchmark for a store category: how far AI agents get at each stage, the stalls that stop them most often, and the score spread. Aggregate figures only, never a named store, published under CC BY 4.0. Use "all" for every store. An unknown category answers with the list of published ones.
Input Schema
{
"type": "object",
"properties": {
"category": {
"type": "string",
"pattern": "^[a-z0-9-]{1,64}$",
"description": "A category slug, e.g. \"fashion\", or \"all\""
}
},
"required": [
"category"
]
}Output Schema
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The dataset’s name."
},
"category": {
"type": "string",
"description": "The category slug, or all."
},
"url": {
"type": "string",
"description": "The benchmark page on ottom.io."
},
"summary": {
"type": "string",
"description": "The benchmark in a few sentences."
},
"methodology": {
"type": "string",
"description": "How the figures are made."
},
"license": {
"type": "string",
"description": "The licence the figures are published under."
},
"metrics": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {},
"description": "The figures: how far AI agents get at each stage, the most common stalls and the score spread. The same document as /benchmarks/{category}/data.json."
}
},
"required": [
"name",
"category",
"url",
"summary",
"methodology",
"license",
"metrics"
],
"additionalProperties": {}
}🟢list_checks
Lists what check_store_readiness reads on a store, what it never does, and what a full scan on ottom.io adds.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"lightCheck": {
"type": "object",
"properties": {
"checks": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "A stable identifier."
},
"name": {
"type": "string",
"description": "What is checked."
},
"what": {
"type": "string",
"description": "What the check looks for."
}
},
"required": [
"id",
"name",
"what"
],
"additionalProperties": false
},
"description": "What check_store_readiness reads."
},
"limits": {
"type": "string",
"description": "How much one check reads, and the daily limits."
},
"neverDone": {
"type": "array",
"items": {
"type": "string"
},
"description": "What the light check never does."
}
},
"required": [
"checks",
"limits",
"neverDone"
],
"additionalProperties": false,
"description": "The light check behind check_store_readiness."
},
"fullScan": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "ottom.io, where a full scan starts."
},
"note": {
"type": "string",
"description": "What a full scan adds."
}
},
"required": [
"url",
"note"
],
"additionalProperties": false,
"description": "A full scan, in which an AI agent tries to buy."
}
},
"required": [
"lightCheck",
"fullScan"
],
"additionalProperties": false
}Community
Evidence