prompt-protection
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Description as published in the official MCP registry.
Maintain this server? Get the badge
What we measured
| Endpoint | None listed (runs locally) | registry |
|---|---|---|
| Website | mughalhere.github.io/prompt-protection | registry |
| GitHub stars | 3 | github.com/mughalhere/prompt-protection |
| Last push | 2026-11-13 | GitHub API |
| Licence | MIT | GitHub API |
| Registry version | 4.4.0 · active · updated 2026-11-05 | registry |
| Package | npm: prompt-protection | registry |
Packages
npm: prompt-protection
Exists · metadata read 2026-11-21
Latest version: 4.4.0. Last published: 2026-11-05.
Deprecated: no.
Weekly downloads: 1,426 · read 2026-11-21. downloads include bots and CI.
Signed reports
No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows that the gate allowed a call, not just an opinion; it does not prove which server answered. How to file one.
Connect
npx -y prompt-protectionCommands are built from the registry entry. Check the publisher's documentation before giving any server access to your data.
Related servers
- Context Nest A shared, governed brain for AI agents: versioned context with approvals, local or hosted.
- fillprompt Search 6,700+ free AI image, video and text prompts and fill them in for your task.
- SafePrompt Detect prompt injection, jailbreaks, and code injection in untrusted text before it…
- GodPrompt MCP Server GodPrompt MCP + Agent Skill for code review, requirements, test planning, and…
- x402-seller — rug protection & safe-alpha for trading agents Rug-check & launch radar for trading agents: composite honeypot score, EVM+Solana, keyless…
- Prompt Injection Scanner Check text before your agent reads it: hidden instructions, invisible text and links that…
Is this your server?
Show the result of our latest check where your users look first. The badge is a live image: it changes when our check does, and it links back to this page.
[](https://openforallofus.com/tools/io.github.mughalhere/prompt-protection)<a href="https://openforallofus.com/tools/io.github.mughalhere/prompt-protection"><img src="https://openforallofus.com/badge/io.github.mughalhere/prompt-protection.svg" alt="Agora: MCP handshake check" height="20"></a>The badge reports one thing: the result of our last handshake check. A server with no remote endpoint shows as "runs locally". How we check.
Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name io.github.mughalhere/prompt-protection.