io.purchaseiq/mcp
Pre-purchase trust checks for AI agents: recalls, scam signals, proceed/caution/avoid verdict.
Open source Repository Open in the app JSON README (API)
About
Pre-purchase trust checks for AI agents: recalls, scam signals, proceed/caution/avoid verdict.
Details
- Kind
- MCP servers
- Topic
- No topic detected
- Publisher
- io.purchaseiq
- Origin
- official
- Category
- ferramentas
- Transport
- http
- Version
- 0.1.0
- Last push
- 2026-08-03T17:04:39Z
- Repository state
- ativo
- License
- MIT
- Added
- 2026-08-29 04:01:45
- Updated
- 2026-08-29 04:01:45
- Origin id
io.purchaseiq/mcp
README
# PurchaseIQ MCP Server
**Pre-purchase trust intelligence for AI agents.** One tool call before checkout: product recalls (46,000+ records across US/EU/CA/FR), seller credibility, scam and phishing signals, and an AI trust verdict, aggregated from 15+ verified sources.
This repository hosts the [MCP Registry](https://registry.modelcontextprotocol.io) manifest for the hosted PurchaseIQ server. The server itself is remote — there is nothing to install or run.
## Endpoint
```
https://purchaseiq.io/api/mcp
```
Transport: Streamable HTTP (stateless JSON-RPC over POST). Registry name: `io.purchaseiq/mcp`.
## Connect
**Claude Code**
```bash
claude mcp add --transport http purchaseiq https://purchaseiq.io/api/mcp
```
**Cline (VS Code)** — add to `cline_mcp_settings.json` (Cline panel → MCP Servers → *Configure MCP Servers*). The `"type"` field is required: without it Cline defaults to the legacy SSE transport, and this server is POST-only streamable HTTP, so the connection fails with a 405.
```json
{
"mcpServers": {
"purchaseiq": {
"type": "streamableHttp",
"url": "https://purchaseiq.io/api/mcp"
}
}
}
```
Then reload the window (Command Palette → *Developer: Reload Window*). Step-by-step agent instructions: [llms-install.md](llms-install.md).
**Cursor, Claude Desktop & other MCP clients** — add to your MCP config (`mcp.json` / `claude_desktop_config.json`):
```json
{
"mcpServers": {
"purchaseiq": {
"url": "https://purchaseiq.io/api/mcp"
}
}
}
```
**Claude.ai** — Settings → Connectors → *Add custom connector* → paste the endpoint URL.
**ChatGPT** — Settings → Connectors → *Create* (developer mode) → paste the endpoint URL.
## The tool: `analyze_purchase`
Pass whatever the agent has — all inputs optional, at least one required:
| Input | Description |
|---|---|
| `url` | Product or store URL |
| `company` | Seller or company name |
| `product` | Product name or description |
| `barcode` | EAN, GTIN, or UPC barcode |
| `country` | ISO country code (default: US) |
Response is a compact agent verdict:
```json
{
"verdict": "caution",
"score": 55,
"topFlags": [
"Domain registered 3 months ago",
"No company registration found",
"SSL valid, TLS 1.3"
],
"reason": "Very new domain with no verifiable company behind it."
}
```
`verdict` is `proceed`, `caution`, or `avoid`. `score` is 0–100. `topFlags` lists up to three highest-priority signals, dangers first.
## Limits & API keys
- **Free tier**: 10 trust checks (`tools/call`) per day per IP. Protocol handshakes (`initialize`, `tools/list`) are always free.
- **API key**: send `Authorization: Bearer <key>` to the same endpoint — no daily limit. Get a key at [purchaseiq.io/mcp](https://purchaseiq.io/mcp).
## Links
- Docs: https://purchaseiq.io/mcp
- Website: https://purchaseiq.io
- Contact: contact@purchaseiq.io
## Disclaimer
PurchaseIQ provides automated, informational risk signals derived from public
data sources. Output is **not** financial, legal, or purchasing advice, and a
"proceed" verdict is not an endorsement or guarantee. Verify independently
before acting. Full terms: https://purchaseiq.io/terms
## License
Documentation in this repository is MIT licensed — see [LICENSE](LICENSE).