mcp

dev.safeprompt/mcp · v0.1.0

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

Description supplied by the publisher in the MCP Registry. We have not tested this server.

Install

npx -y @safeprompt.dev/mcp

Assembled from the package metadata in the official MCP Registry (including any subcommand or flag the publisher lists). Some publishers do not list the subcommand that starts MCP mode, so confirm the command in the README, along with any required configuration and credentials, before connecting it to real data.

Signals

GitHub stars	2
npm weekly downloads	0
Last push	11d ago
Licence	MIT
Open issues	0
SECURITY.md	Yes
Language	Python
Latest version published	2026-06-22

Signals captured from GitHub, npm and the official MCP Registry on October 17, 2026. See the scoring method.

Similar servers

Lexicon

Score 77

Fixes the names and jargon speech-to-text gets wrong before your agent acts on a dictated prompt.

★ 2↓ 48/wkMITpushed today

AI & media

Clipboard

Score 78

Read and write the system clipboard — tables, text, code, JSON, URLs, images, and more.

★ 4Apache-2.0pushed 4d ago

AI & media

Agent Readiness Auditor

Score 71

Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.

★ 1↓ 240/wkMITpushed 6d ago

AI & mediaSearch & web