Which stores let AI agents buy. Free, read-only, no key.
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.
Summarize which retailers' public robots.txt files name AI agents, and where to read the full check. robots.txt is a request, not proof of a block. Credit the blocklist page.
This tool takes no arguments.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http feed https://agent-shopping-tracker.vercel.app/api/mcp
Summarize which retailers' public robots.txt files name AI agents, and where to read the full check. robots.txt is a request, not proof of a block. Credit the blocklist page.
No arguments.
{
"type": "object",
"properties": {}
}Look up one tracker row by slug, such as walmart or etsy. Credit the Page URL in the result. Keep the note. It is uncertainty.
| Argument | Type | Description |
|---|---|---|
| slug* | string | Player slug, such as walmart or etsy. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "Player slug, such as walmart or etsy."
}
}
}List every store, platform, payment network, and protocol on the Agent Shopping Tracker, with status and the page to credit.
No arguments.
{
"type": "object",
"properties": {}
}Search dated news. Filter with since (YYYY-MM-DD), a player slug, or words from the title, summary, or tags. Credit each item's Page URL.
| Argument | Type | Description |
|---|---|---|
| limit | integer | How many items to return. Default 20. |
| query | string | Words to find in the title, summary, tags, or source name. |
| since | string | Only news on or after this date, YYYY-MM-DD. |
| player | string | Player slug, such as walmart. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "How many items to return. Default 20."
},
"query": {
"type": "string",
"description": "Words to find in the title, summary, tags, or source name."
},
"since": {
"type": "string",
"description": "Only news on or after this date, YYYY-MM-DD."
},
"player": {
"type": "string",
"description": "Player slug, such as walmart."
}
}
}List retailers whose public robots.txt disallows an AI agent token, fully or partly. Pass a token such as GPTBot or ChatGPT-User, or omit it for any tracked agent. Credit the blocklist page. A disallow is not proof the site enforces it.
| Argument | Type | Description |
|---|---|---|
| match | string | full means a whole-site disallow. partial means only some paths. either is the default. |
| token | string | Agent token, such as GPTBot, ChatGPT-User, ClaudeBot, or PerplexityBot. Omit for any tracked agent. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"match": {
"enum": [
"full",
"partial",
"either"
],
"type": "string",
"description": "full means a whole-site disallow. partial means only some paths. either is the default."
},
"token": {
"type": "string",
"description": "Agent token, such as GPTBot, ChatGPT-User, ClaudeBot, or PerplexityBot. Omit for any tracked agent."
}
}
}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 10, 2026.
Takes a password, API key or token as an argument, so the secret passes through the model's context and chat logs.
Fix: Read credentials from the server's own configuration (environment, OAuth) instead of a tool argument.