io.github.GSterlingPress/recover

up checked 2026-11-11T09:39:03.365Z

Unclaimed · Unverified

Publisher-provided title

RECOVER — Decide Safely After a Failed Machine Action

Publisher-provided description

Choose the safest next action after an API, MCP, or agent failure before retrying.

Summary by lookupd

Recommends the safest next step after a failed API, tool, or agent action, so an agent can decide whether to retry, stop, or escalate.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http recover https://recover-api-production-bbba.up.railway.app/mcp

Codex, remote (streamable-http)

codex mcp add recover --url https://recover-api-production-bbba.up.railway.app/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "recover": {
      "url": "https://recover-api-production-bbba.up.railway.app/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

recover_decide Use immediately after an API, MCP tool, automation, or agent action fails and before retrying. Especially use after timeouts, 5xx/429 responses, uncertain execu

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.GSterlingPress/recover.svg)](https://lookupd.com/servers/io.github.GSterlingPress/recover)