Weibo hot search, post search/details, comments/replies, users, posts, transcript.
Web & Searchv0.1.1streamable-httpmcp.52choujiang.com
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 70ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo weibo_mcp@3.0.0 |
| tooling | 30 / 35 | tools/list OK: 18 tools e.g. "weibo_search_posts"; 18/18 described, 18/18 fully-typed schemas, median description 39 chars |
| latency | 10 / 10 | initialize round-trip 70ms |
| provenance | 12 / 15 | description present; no repository URL; version 0.1.1; namespace com.52choujiang matches endpoint/repo |
Score 92/100 · latency 70ms · 18 tools · auth: open
Claude Code:
claude mcp add --transport http weibo-insights https://mcp.52choujiang.com/weibo/mcp
Generic MCP client config:
{ "mcpServers": { "weibo-insights": { "type": "http", "url": "https://mcp.52choujiang.com/weibo/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/com.52choujiang/weibo-insights · referral link https://mcpqueen.com/go/com.52choujiang/weibo-insights (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/com.52choujiang/weibo-insights)
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 |
|---|---|---|---|
| 2026-07-12 21:45 | A | 92 | 70ms |