Open-source MCP and HTTPS screening for prompts, skills, and tool descriptions using TypeSafe AI Jev, deterministic checks, and configurable reasoning.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add promptrejectormcp --env YOUR_API_KEY='<YOUR_API_KEY>' -- npx -y prompt-rejector~/.codex/config.toml
[mcp_servers.promptrejectormcp]
command = "npx"
args = ["-y", "prompt-rejector"]
env = { YOUR_API_KEY = "<YOUR_API_KEY>" }
# codex mcp add promptrejectormcp --env YOUR_API_KEY='<YOUR_API_KEY>' -- npx -y prompt-rejector~/.cursor/mcp.json
{
"mcpServers": {
"promptrejectormcp": {
"command": "npx",
"args": [
"-y",
"prompt-rejector"
],
"env": {
"YOUR_API_KEY": "<YOUR_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"promptrejectormcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"prompt-rejector"
],
"env": {
"YOUR_API_KEY": "<YOUR_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"promptrejectormcp": {
"command": "npx",
"args": [
"-y",
"prompt-rejector"
],
"env": {
"YOUR_API_KEY": "<YOUR_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"promptrejectormcp": {
"command": "npx",
"args": [
"-y",
"prompt-rejector"
],
"env": {
"YOUR_API_KEY": "<YOUR_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"promptrejectormcp": {
"command": "npx",
"args": [
"-y",
"prompt-rejector"
],
"env": {
"YOUR_API_KEY": "<YOUR_API_KEY>"
}
}
}
}Environment variables
YOUR_API_KEY
Replace the placeholders with your own credentials and keep them out of version control.