Product search, price comparison, and deal discovery for AI agents across Singapore, SEA, and US.
Dev & Codev1.0.5streamable-httpapi.buywhere.ai repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 1296ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2024-11-05, serverInfo buywhere-catalog@1.0.0 |
| tooling | 35 / 35 | tools/list OK: 8 tools e.g. "search_products"; 8/8 described, 8/8 fully-typed schemas, median description 203 chars |
| latency | 7 / 10 | initialize round-trip 1296ms |
| provenance | 15 / 15 | description present; repository linked; version 1.0.5; namespace io.github.BuyWhere matches endpoint/repo |
Score 97/100 · latency 1296ms · 8 tools · auth: open
Claude Code:
claude mcp add --transport http buywhere-mcp https://api.buywhere.ai/mcp
Generic MCP client config:
{ "mcpServers": { "buywhere-mcp": { "type": "http", "url": "https://api.buywhere.ai/mcp" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/io.github.BuyWhere/buywhere-mcp · referral link https://mcpqueen.com/go/io.github.BuyWhere/buywhere-mcp (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.BuyWhere/buywhere-mcp)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-13 14:16 | A | 97 | 1296ms |