MCP server for AI agent security -- input validation, prompt injection detection, PII redaction, policy enforcement, rate limiting, and audit logging
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add guardrails -- npx -y guardrails-mcp-server~/.codex/config.toml
[mcp_servers.guardrails]
command = "npx"
args = ["-y", "guardrails-mcp-server"]
# codex mcp add guardrails -- npx -y guardrails-mcp-server~/.cursor/mcp.json
{
"mcpServers": {
"guardrails": {
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}.vscode/mcp.json
{
"servers": {
"guardrails": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"guardrails": {
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"guardrails": {
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"guardrails": {
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}