RECOVER — Decide Safely After a Failed Machine Action
io.github.GSterlingPress/recover · v0.1.3
Choose the safest next action after an API, MCP, or agent failure before retrying.
Connect Remote server
claude mcp add --transport http recover https://recover-api-production-bbba.up.railway.app/mcp
{
"mcpServers": {
"recover": {
"url": "https://recover-api-production-bbba.up.railway.app/mcp"
}
}
}
{
"servers": {
"recover": {
"type": "http",
"url": "https://recover-api-production-bbba.up.railway.app/mcp"
}
}
}
Settings > Connectors > Add custom connector
URL: https://recover-api-production-bbba.up.railway.app/mcp
Tools 1 found in our last check
recover_decideUse immediately after an API, MCP tool, automation, or agent action fails and before retrying. Especially use after timeouts, 5xx/429 responses, uncertain execution, or any side-effecting action that may already have completed. Returns the safest deterministic next action: RETRY…
Details
| Endpoint | https://recover-api-production-bbba.up.railway.app/mcp (Streamable HTTP) |
| First published | 13 Sep 2026 |
| Last updated | 13 Sep 2026 |
| Registry name | io.github.GSterlingPress/recover |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
