
Search Amazon, eBay, Walmart and more and compare prices. Agents can search, not buy.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Narrow towards a purchase without inventing keywords. One call returns children[] and childrenDeep[] with estimated counts, brands[] each with an engineParam you can pass straight back to search_products.engineParam, the shop's own facets[], aspectTiles[], siblings[], related[] and a deals[] rail. GET /api/agent/browse/tree/<slug>, or GET /api/agent/browse/tree/<slug>/<nodeId> for any category under a department. No wallet and no signature. contentAt is when those deal prices were read: send it as a candidate's priceAt to compare_landed_cost, which is the shortlist this call is meant to fill. Counts are estimates and countScope says so. A shelf already read answers from cache; a cold one costs one call against the catalogue quota shared with shoppers, so read the shelf you want rather than walking the tree.
The `slug` field of a department from list_categories.
A category id under that department, from children[].id or childrenDeep[].id. Omit for the department itself.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http escrova https://www.escrova.io/api/mcp
Narrow towards a purchase without inventing keywords. One call returns children[] and childrenDeep[] with estimated counts, brands[] each with an engineParam you can pass straight back to search_products.engineParam, the shop's own facets[], aspectTiles[], siblings[], related[] and a deals[] rail. GET /api/agent/browse/tree/<slug>, or GET /api/agent/browse/tree/<slug>/<nodeId> for any category under a department. No wallet and no signature. contentAt is when those deal prices were read: send it as a candidate's priceAt to compare_landed_cost, which is the shortlist this call is meant to fill. Counts are estimates and countScope says so. A shelf already read answers from cache; a cold one costs one call against the catalogue quota shared with shoppers, so read the shelf you want rather than walking the tree.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The `slug` field of a department from list_categories. |
| nodeId | string | A category id under that department, from children[].id or childrenDeep[].id. Omit for the department itself. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The `slug` field of a department from list_categories."
},
"nodeId": {
"type": "string",
"description": "A category id under that department, from children[].id or childrenDeep[].id. Omit for the department itself."
}
}
}For a "find something on offer" task. GET /api/agent/browse/deals?tab=<tab>, where tab is markdowns, refurbished, top-rated, brands, or door:<slug> for one department. No wallet and no signature. Every item carries cachedAt, which is when that price was true: pass it as a candidate's priceAt to compare_landed_cost. A selection over rows this site has already cached, so it costs no catalogue call. An unknown tab is refused with 400 rather than guessed at. A sticker discount is not a cheaper order: rank with compare_landed_cost before you quote.
| Argument | Type | Description |
|---|---|---|
| tab* | string | markdowns, refurbished, top-rated, brands, or door:<slug> with a slug from list_categories. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"tab"
],
"properties": {
"tab": {
"type": "string",
"description": "markdowns, refurbished, top-rated, brands, or door:<slug> with a slug from list_categories."
}
}
}Every department, the groups under it and the links under those, for picking a shelf in one read rather than walking down to it. GET /api/agent/browse/directory. No wallet and no signature. Built ONLY from rows already cached, so it costs no catalogue call at all and a picture or count nobody has fetched yet comes back null rather than being fetched for you. Prefer this over repeated get_category calls when you are still deciding where to look.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}The current fee schedule and delivery rates, so a total can be explained before anyone pays it. GET /api/config/fees. No wallet and no signature.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Current USD prices of the coins shown on Escrova. GET /api/prices. No wallet and no signature. Checkout on this deployment takes USDC only.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Returns the current Terms of Service and Privacy Policy version and document hash. These are the exact values accept_terms will record; they are read server-side and never taken from your request. GET /api/agent/legal/terms. No wallet and no signature.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Start a shopping task here instead of guessing search words. Returns the sixteen departments, each with the slug get_category takes and a picture. A keyword search is one guess at what somebody meant; a department is the shop's own shelf, and get_category on one hands you the brands, the filters and a page of listings in a single call. GET /api/agent/browse/categories. No wallet and no signature. Served from cache; a department whose picture has gone cold costs one call against the catalogue quota this site shares with its shoppers.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Search products across the marketplaces Escrova can actually buy from today. Six sources are searchable: amazon, ebay, walmart, bestbuy, homedepot, wayfair, or "all". GET /api/products/search. No wallet and no signature. Send q, cat, or both; page and every selected filter are preserved together. A brands[].engineParam returned by get_category goes into engineParam here and is sent as the typed eBay aspect filter, while Google refinements use shoprs. The REST pagination and degraded-source metadata are returned unchanged. A search is one guess at what somebody meant and it spends a paid provider call; when you know roughly what department a thing is in, list_categories and get_category narrow further for less.
| Argument | Type | Description |
|---|---|---|
| q | string | What to search for. Optional when cat is supplied. |
| cat | string | Department slug, category id, or <id>-<slug> returned by get_category. |
| page | integer | |
| sort | string | |
| limit | integer | |
| shoprs | string | A Google filter option whose engineParamType is shoprs. |
| source | string | |
| maxPrice | number | |
We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 4, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.
| minPrice |
| number |
| minRating | number |
| engineParam | string | A brands[].engineParam from get_category; sent only as ebayAspectFilter. |
| freeShipping | boolean |
| ebayCategoryId | string |
| ebayAspectFilter | string |
| ebayConditionIds | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"q": {
"type": "string",
"maxLength": 300,
"description": "What to search for. Optional when cat is supplied."
},
"cat": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Department slug, category id, or <id>-<slug> returned by get_category."
},
"page": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"sort": {
"enum": [
"price_asc",
"price_desc"
],
"type": "string"
},
"limit": {
"type": "integer",
"maximum": 60,
"minimum": 1
},
"shoprs": {
"type": "string",
"maxLength": 4000,
"minLength": 1,
"description": "A Google filter option whose engineParamType is shoprs."
},
"source": {
"enum": [
"amazon",
"ebay",
"walmart",
"bestbuy",
"homedepot",
"wayfair",
"all"
],
"type": "string"
},
"maxPrice": {
"type": "number",
"minimum": 0
},
"minPrice": {
"type": "number",
"minimum": 0
},
"minRating": {
"type": "number",
"maximum": 5,
"minimum": 0
},
"engineParam": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "A brands[].engineParam from get_category; sent only as ebayAspectFilter."
},
"freeShipping": {
"type": "boolean"
},
"ebayCategoryId": {
"type": "string",
"maxLength": 100,
"minLength": 1
},
"ebayAspectFilter": {
"type": "string",
"maxLength": 4000,
"minLength": 1
},
"ebayConditionIds": {
"type": "string",
"maxLength": 500,
"minLength": 1
}
}
}