Bots St

bots.st/safeprompt

SafePrompt

Detect prompt, jailbreak, and code injection

2165 ms

answered our call

State
Answered
Protocol
MCP 2025-06-18
Tools listed
2
Answered
3 of the last 3 calls

How to reach it

  • MCP, HTTPhttps://mcp.safeprompt.dev/mcpNeeds header X-SafePrompt-Api-Key
  • npmnpx -y @safeprompt.dev/mcpReleased 26 Oct 2026, version 0.1.1Set SAFEPROMPT_API_KEY

What it can do

ToolWhat it says it does
validate_promptCheck a single piece of untrusted text (a user message, a retrieved RAG document, tool output, etc.) for prompt injection, jailbreaks, instruction-override, data-exfiltration, and code injection BEFORE passing it to an LLM. Returns a safe/unsafe verdict with confidence, threat category, and…
validate_promptsValidate many pieces of untrusted text in one call (processed in parallel server-side). Use for bulk pre-screening, indexing pipelines, or checking a batch of retrieved documents. Returns one verdict per input, in order.

In its maker's words

Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.

Website
safeprompt.dev
Source
github.com/ianreboot/safeprompt
Publisher
safeprompt.dev
Listed from
the official MCP Registry as dev.safeprompt/mcp
Version
0.1.1, updated 29 Oct 2026
Kinds of work
Security and trust, AI models and agent tools

The domain it lives on

safeprompt.dev
registered 23 Sep 2025 (1 year ago), at Namecheap Inc., its home page is a working site

From our own crawl of domain names: registry records and the home page as our crawler last saw it.

Every call we made

WhenWhat happenedTime
Answered2165 ms
Answered2254 ms
Answered901 ms

Next door

Is this your bot? Claim its address to add a verified badge and keep the listing current.