Promptrejectormcp
by revsmokecommunityv1.0.1
1
2
Prompt Rejector is a security gateway that protects AI applications from prompt injection attacks and other web vulnerabilities by screening untrusted input before it reaches the agent's control plane.
From the registry: Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
Install & configure
Prerequisites
- requiredClone and buildClone repo, install dependencies, configure GEMINI_API_KEY
https://aistudio.google.com/apikey$ git clone https://github.com/revsmoke/promptrejectormcp.git && cd promptrejectormcp && npm install && echo "GEMINI_API_KEY=your_key" > .env && npm run build
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `promptrejectormcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Clone and build** — Clone repo, install dependencies, configure GEMINI_API_KEY Run: `git clone https://github.com/revsmoke/promptrejectormcp.git && cd promptrejectormcp && npm install && echo "GEMINI_API_KEY=your_key" > .env && npm run build` (https://aistudio.google.com/apikey)
Canonical MCP server config (stdio transport):
- command: `node`
- args: ["dist/index.js"]
- required environment variables:
- `GEMINI_API_KEY`: Google Gemini API key for AI-based prompt injection detection (example: `<your-gemini-api-key>`)
Note: Dual-layer security gateway for AI agents. Detects prompt injection, jailbreaks, XSS, SQLi. HTTP endpoint also available at localhost:3000. Requires build from source.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: Dual-layer security gateway for AI agents. Detects prompt injection, jailbreaks, XSS, SQLi. HTTP endpoint also available at localhost:3000. Requires build from source.
Tools (5)
check_prompt
Check user prompts for injection attacks
scan_skill
Scan SKILL.md files for security vulnerabilities
list_patterns
List all detection patterns with optional filtering
update_vuln_feeds
Scan NVD + GitHub Advisory feeds for new CVE-based patterns
verify_pattern_integrity
Check SHA-256 + HMAC integrity of the pattern library
Environment variables
GEMINI_API_KEYrequiredYour Google AI API keyPackages
prompt-rejector
npmv1.0.1transport: stdio
Details
- Language
- TypeScript
- License
- ISC
- Released
- Jan 28, 2026
- Last commit
- May 18, 2026
- Registry name
- io.github.revsmoke/promptrejectormcp