Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

We stopped reading 2,195 MCP servers for three days. Another team's log is how we found out

说明与用途

HISTOR 在升级 MCP 协议后停止读取 2,195 台服务器,但仪表盘未显示警报。通过与独立日志比较发现问题,更新客户端后恢复了所有读取。

问题

HISTOR’s MCP reader stopped reading 2,195 servers after a protocol change, but dashboards showed no alerts.

结果

The reader resumed reading all affected servers; protocol‑version statistics revealed 19 % of servers support the new 2026‑07‑28 revision.

工作流

  • 1. Detect missing reads via comparison with a second log (ScraperWatch).
  • 2. Identify error patterns (HTTP 401/403, legacy error IDs, missing supportedVersions).
  • 3. Update reader to fall back to initialize on any of those patterns.
  • 4. Deploy fix (08:44:57 UTC 1 Nov).
  • 5. Verify reads resume and success metrics recover.

证据

HISTOR’s reader learned the new revision and started trying it first. We made the fallback strict on purpose.

来源

The reader now follows the specification's rule as written. It falls back to initialize, once, when the first new‑style request is refused.

来源

The fix went live on 1 November at 08:44:57 UTC. In the first 90 seconds, 171 of 172 remote reads succeeded, and 145 of those used an older protocol.

来源

  • 记录日期: 2026-11-02T09:43:47.791Z