Safeprompt runs on your own machine — the client starts it, so there is no endpoint to ping. 37 installs a week from npm. Last commit 17 Sep 2026.
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
We read the source, 19 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp -- npx -y @safeprompt.dev/mcp
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@safeprompt.dev/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@safeprompt.dev/mcp"]
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@safeprompt.dev/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@safeprompt.dev/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SAFEPROMPT_API_KEY (SafePrompt API key from https://dashboard.safeprompt.dev), SAFEPROMPT_PROVIDER (API base URL (default https://api.safeprompt.dev)), SAFEPROMPT_USER_IP (Value sent as X-User-IP for threat-intel tracking (default 203.0.113.1)).
The author declared them in the registry entry; get the values from the project itself.
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
Local-first PHI detection for source code, LLM prompts, logs, and analytics
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
Catch spec drift before it catches you. Detect overlap, stale docs, and code drift.
24 checks on the register CSV before it reaches the supervisor — LEI check digits, ISO dates and cod
Copyright deposit API — protect code, text, and websites with Berne Convention proof
Check whether a Claude Code skill was tested and whether it works before installing it.
AI text detection and humanization for Claude Code, Cursor, and Windsurf.
Answers built from our own checks of this server.