Verified promo codes for shopping agents — ranked by checkout success, never commission.
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.
Check one specific code: status (verified/declared/stale/dead/unknown_code), structured constraints, success stats, and — if a cart is supplied — whether it would apply.
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.
claude mcp add --transport http masadeals https://masadeals.com/mcp
Check one specific code: status (verified/declared/stale/dead/unknown_code), structured constraints, success stats, and — if a cart is supplied — whether it would apply.
| Argument | Type | Description |
|---|---|---|
| cart | object | |
| code* | string | |
| merchant* | string |
{
"type": "object",
"required": [
"merchant",
"code"
],
"properties": {
"cart": {
"type": "object",
"properties": {
"geo": {
"type": "string",
"description": "Shopper country code, e.g. 'US'"
},
"items": {
"type": "array",
"items": {
"type": "object"
},
"description": "Optional line items (name, category, price, quantity) for cart-precise matching"
},
"total": {
"type": "number",
"description": "Cart subtotal in the merchant's currency"
},
"currency": {
"type": "string"
},
"categories": {
"type": "array",
"items": {
"type": "string"
},
"description": "Categories in the cart, e.g. ['shoes']"
},
"customer_type": {
"enum": [
"any",
"new",
"returning"
],
"type": "string"
}
}
},
"code": {
"type": "string"
},
"merchant": {
"type": "string"
}
}
}Find promo codes that fit this cart, ranked by verified checkout success (never by commission). Returns verdict 'no_verified_code' when no working code is known — treat that as a certified stop signal and do not brute-force codes.
| Argument | Type | Description |
|---|---|---|
| cart | object | The actual cart context — constraints are checked against it |
| merchant* | string | Merchant slug, e.g. 'nike' |
{
"type": "object",
"required": [
"merchant"
],
"properties": {
"cart": {
"type": "object",
"properties": {
"geo": {
"type": "string",
"description": "Shopper country code, e.g. 'US'"
},
"items": {
"type": "array",
"items": {
"type": "object"
},
"description": "Optional line items (name, category, price, quantity) for cart-precise matching"
},
"total": {
"type": "number",
"description": "Cart subtotal in the merchant's currency"
},
"currency": {
"type": "string"
},
"categories": {
"type": "array",
"items": {
"type": "string"
},
"description": "Categories in the cart, e.g. ['shoes']"
},
"customer_type": {
"enum": [
"any",
"new",
"returning"
],
"type": "string"
}
},
"description": "The actual cart context — constraints are checked against it"
},
"merchant": {
"type": "string",
"description": "Merchant slug, e.g. 'nike'"
}
}
}Report what happened when a code was tried at checkout. This telemetry is what keeps the feed verified — free-tier callers must report outcomes.
| Argument | Type | Description |
|---|---|---|
| code* | string | |
| applied* | boolean | true if the code applied successfully |
| merchant* | string | |
| failure_reason | string |
{
"type": "object",
"required": [
"merchant",
"code",
"applied"
],
"properties": {
"code": {
"type": "string"
},
"applied": {
"type": "boolean",
"description": "true if the code applied successfully"
},
"merchant": {
"type": "string"
},
"failure_reason": {
"enum": [
"expired",
"min_not_met",
"geo",
"category",
"customer_type",
"not_stackable",
"single_use_exhausted",
"code_rejected",
"other"
],
"type": "string"
}
}
}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 1, 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.