
Security News
Re-Enabled GitHub Actions Expose Thousands of Repositories to Mini Shai-Hulud
Two compromised GitHub Actions were re-enabled with malicious tags intact, exposing thousands of downstream repositories to Mini Shai-Hulud.
@prompt-ot/mcp
Advanced tools
Model Context Protocol server for PromptOT — manage, edit, and publish prompts from Claude Desktop, Cursor, Codex, ChatGPT, and any other MCP-compatible AI tool.
Model Context Protocol server for PromptOT.
Use PromptOT directly from Claude Desktop, Cursor, Codex CLI, ChatGPT, claude.ai, or any other MCP-compatible AI tool. The server exposes ~35 tools for managing prompts, blocks, variables, versions, test cases, and more — all gated by scoped API keys.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"promptot": {
"command": "npx",
"args": ["-y", "@prompt-ot/mcp"],
"env": {
"PROMPTOT_API_KEY": "pot_...",
"PROMPTOT_MCP_CLIENT": "claude-desktop"
}
}
}
}
Generate your API key from the PromptOT dashboard → project → API Keys → "Generate MCP Key".
Add to ~/.cursor/mcp.json (or .cursor/mcp.json in your workspace root):
{
"mcpServers": {
"promptot": {
"command": "npx",
"args": ["-y", "@prompt-ot/mcp"],
"env": {
"PROMPTOT_API_KEY": "pot_...",
"PROMPTOT_MCP_CLIENT": "cursor"
}
}
}
}
Add to ~/.codex/config.toml:
[mcp_servers.promptot]
command = "npx"
args = ["-y", "@prompt-ot/mcp"]
env = { PROMPTOT_API_KEY = "pot_...", PROMPTOT_MCP_CLIENT = "codex-cli" }
The hosted transport is at https://mcp.promptot.com/mcp. Connect via OAuth from the client's MCP settings — no config file needed.
| Variable | Required | Default | Description |
|---|---|---|---|
PROMPTOT_API_KEY | Yes | — | Your scoped API key from the PromptOT dashboard |
PROMPTOT_API_URL | No | https://api.promptot.com | Override for self-hosted or local dev |
PROMPTOT_MCP_CLIENT | No | unknown | Client identifier for analytics (claude-desktop, cursor, codex-cli, etc.) |
PROMPTOT_DEBUG | No | false | Enable verbose stderr logging for troubleshooting |
Full tool reference and FAQ: https://www.promptot.com/docs/mcp
MIT
FAQs
Model Context Protocol server for PromptOT — manage, edit, and publish prompts from Claude Desktop, Cursor, Codex, ChatGPT, and any other MCP-compatible AI tool.
We found that @prompt-ot/mcp demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.

Security News
Two compromised GitHub Actions were re-enabled with malicious tags intact, exposing thousands of downstream repositories to Mini Shai-Hulud.

Research
/Security News
A malicious Firefox extension fetches its payload after installation to evade detection, steal Google session cookies, and automate account takeover.

Research
/Security News
The compromise affects MemTensor's MemOS, an open source memory framework for large language models (LLMs) and AI agents. Both npm package @memtensor/memos-cloud-openclaw-plugin and the PyPI package MemoryOS are compromised. They drop cross-platform Go binaries that exfiltrate developer secrets.