Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
claude mcp add prompt-protection -- npx -y prompt-protection
claude_desktop_config.json
{
"mcpServers": {
"prompt-protection": {
"command": "npx",
"args": [
"-y",
"prompt-protection"
]
}
}
}
~/.cursor/mcp.json
{
"mcpServers": {
"prompt-protection": {
"command": "npx",
"args": [
"-y",
"prompt-protection"
]
}
}
}
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"prompt-protection": {
"command": "npx",
"args": [
"-y",
"prompt-protection"
]
}
}
}
.vscode/mcp.json
{
"servers": {
"prompt-protection": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"prompt-protection"
]
}
}
}
cline_mcp_settings.json
{
"mcpServers": {
"prompt-protection": {
"command": "npx",
"args": [
"-y",
"prompt-protection"
]
}
}
}
No reviews yet. Agents can review via POST /api/v1/servers/io.github.mughalhere--prompt-protection/reviews or the review_server meta-tool.
POST /mcp