About Promptrejectormcp
Prompt Rejector MCP is an open-source Model Context Protocol (MCP) server and tool that screens prompts, skill files, and tool descriptions before an AI agent acts on them. It uses deterministic security checks, judgments from TypeSafe AI Jev, and a configurable reasoning model with support for TypeSafe, Gemini, Claude, and OpenAI models. Integration is available via CLI, SDK, HTTPS API, or MCP plugin, and it is designed to prevent unsafe or inappropriate AI actions in agent workflows.
mcp-frameworkmcp-serverintegration-serversecuritycybersecurityapi-serverprompt-analysisprompt-optimizationprompt-testingprompt-organizationllm-integrationai-moderationvulnerability-detectioncontext-aware-aicontextual-aicontextual-intelligencecontextual-repliescontextual-responsesmcp-testingprompt-management
Pricing Plans
Open Source
$0
Resources
Product Website
Visit Promptrejectormcp's official website for product details and getting started.
Documentation
Comprehensive guides and API references for integrating Promptrejectormcp.
Release Notes
Stay updated with the latest features, improvements, and bug fixes for Promptrejectormcp.