AI & Machine Learning

magicbox.tools

MCP server for the MagicBox.Tools AI tool directory that enables searching, retrieving, submitting, and checking the status of AI tool listings.

1 endpoint4 known toolsFirst detected October 6, 2026Last detected October 6, 2026

ENDPOINT 1

https://magicbox.tools/api/mcp/mcp

No auth detected

Capabilities

tools.listChanged

Search the MagicBox.Tools directory of AI tools.

Inferred read-only

Get details of one listed AI tool by its directory name (the slug from search_tools results, e.g.

Inferred read-only

Submit a tool to the MagicBox.Tools directory.

Inferred read-only

Check the status of one of your MagicBox.Tools submissions by site_id (uuid) or the submitted URL.

Inferred read-only

CONNECT WITH APPROVAL

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

Codex

~/.codex/config.toml

[mcp_servers.magicbox-tools]
url = "https://magicbox.tools/api/mcp/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "magicbox-tools": {
      "type": "http",
      "url": "https://magicbox.tools/api/mcp/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: magicbox-tools
Remote MCP URL: https://magicbox.tools/api/mcp/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": {
    "magicbox-tools": {
      "url": "https://magicbox.tools/api/mcp/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "magicbox-tools": {
      "type": "http",
      "url": "https://magicbox.tools/api/mcp/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "magicbox-tools",
  "transport": "streamable-http",
  "url": "https://magicbox.tools/api/mcp/mcp"
}

MCP Inspector

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

TRUST AND VERIFICATION 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.