← Registry

AI & Machine Learning

aidown.dev

Provides live status information for AI services such as Claude, ChatGPT, Gemini, and GitHub Copilot using independent probes and user reports.

1 endpoint1 known toolsFirst detected October 21, 2026Last detected October 21, 2026

ENDPOINT 1

https://aidown.dev/mcp

No auth detected

MCP server metadata

Name
AI Down
Version
0.1.0
Capabilities
tools
Server instructions

Use get_status when the user asks if an AI tool is down, slow or failing.

Known tools 1

get_status

Live status of an AI service (Claude, Claude Code, ChatGPT, Codex, Gemini, Cursor, GitHub Copilot, OpenRouter) from independent probes and user reports.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.ai-down]
url = "https://aidown.dev/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "ai-down": {
      "type": "http",
      "url": "https://aidown.dev/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: ai-down
Remote MCP URL: https://aidown.dev/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "ai-down": {
      "url": "https://aidown.dev/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "ai-down": {
      "type": "http",
      "url": "https://aidown.dev/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "ai-down",
  "transport": "streamable-http",
  "url": "https://aidown.dev/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.