npm guardrails-mcp-serverstdioMITupdated 11d ago
MCP server for AI agent security guardrails. Provides input validation, prompt injection detection, PII redaction, output filtering, policy enforcement, rate limiting, and comprehensive audit logging.
O que dá para fazer com guardrails?
guardrails-mcp-server
[!License: MIT](https://opensource.org/licenses/MIT) [!MCP](https://modelcontextprotocol.io) [!Node.js](https://nodejs.org)
MCP server for AI agent security guardrails. Provides input validation, prompt injection detection, PII redaction, output filtering, policy enforcement, rate limiting, and comprehensive audit logging.
Tools
| Tool | Description |
|---|---|
validate_input |
Validate and sanitize incoming requests through all guardrail checks |
filter_output |
Filter and redact sensitive data (PII, secrets, credentials) from responses |
check_policy |
Evaluate a request against security policies (RBAC, resource access, quotas) |
get_audit_logs |
Query the audit log with filtering by type, user, time range |
get_stats |
Get engine statistics including active users, block rate, request counts |
update_config |
Update guardrail configuration at runtime |
Security Features
- Prompt Injection Detection -- 12 regex patterns for jailbreak, DAN mode, system prompt override
- PII Detection and Redaction -- SSN, credit card, email, phone, IP, API keys, AWS keys, JWT, passwords, private keys, connection strings
- Malicious Code Blocking -- eval, exec, subprocess, child_process, shell injection
- Policy Engine -- Block sensitive paths, dangerous tools, unauthenticated destructive ops, URL allowlist, maintenance windows
- Rate Limiting -- Per-user sliding window (configurable requests/minute)
- Audit Logging -- Timestamped events with metrics, log rotation, external handler support
Install
npm install
Configuration
{
"mcpServers": {
"guardrails": {
"type": "stdio",
"command": "node",
"args": ["/path/to/guardrails-mcp-server/index.js"]
}
}
}
Project Structure
src/engine/GuardrailsEngine.js # Core orchestration
src/validators/InputValidator.js # Prompt injection and PII detection
src/filters/OutputFilter.js # Redaction and harmful content blocking
src/policies/PolicyEngine.js # RBAC, quotas, maintenance windows
src/audit/AuditLogger.js # Event logging and metrics
License
Instalação
Adicione guardrails ao seu cliente. Escolha o que você usa.
claude mcp add guardrails-mcp-server -- npx -y guardrails-mcp-servercodex mcp add guardrails-mcp-server -- npx -y guardrails-mcp-serveramp mcp add guardrails-mcp-server -- npx -y guardrails-mcp-server{
"mcpServers": {
"guardrails-mcp-server": {
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}Add to `claude_desktop_config.json`, then restart Claude Desktop.
{
"mcpServers": {
"guardrails-mcp-server": {
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}Add to `~/.cursor/mcp.json`, or `.cursor/mcp.json` for a single project.
code --add-mcp '{"name":"guardrails-mcp-server","command":"npx","args":["-y","guardrails-mcp-server"]}'Or add the block manually to `.vscode/mcp.json` under `servers`.
{
"mcpServers": {
"guardrails-mcp-server": {
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}Add to `~/.codeium/windsurf/mcp_config.json`.
{
"mcpServers": {
"guardrails-mcp-server": {
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}Add to `cline_mcp_settings.json` via the MCP Servers panel.
{
"mcpServers": {
"guardrails-mcp-server": {
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}Add to `~/.gemini/settings.json`.
{
"mcpServers": {
"guardrails-mcp-server": {
"type": "local",
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
],
"tools": [
"*"
]
}
}
}Add to `~/.copilot/mcp-config.json`, or run `/mcp add` inside the CLI.
{
"context_servers": {
"guardrails-mcp-server": {
"command": {
"path": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}
}Add to your Zed `settings.json`.
npx -y guardrails-mcp-serverRun `goose configure`, choose **Add Extension → Command-line Extension**, and paste this command.
6 ferramentas
guardrails expõe 6 ferramentas a um agente conectado.
- validate_input
- Validate and sanitize incoming requests through all guardrail checks
- filter_output
- Filter and redact sensitive data (PII, secrets, credentials) from responses
- check_policy
- Evaluate a request against security policies (RBAC, resource access, quotas)
- get_audit_logs
- Query the audit log with filtering by type, user, time range
- get_stats
- Get engine statistics including active users, block rate, request counts
- update_config
- Update guardrail configuration at runtime
Pontuação
72 / 100
Boa
- Documentação22/25
- Manutenção19/25
- Confiança13/20
- Capacidade6/15
- Instalação12/15
- Documents what it does and how to connect
- Has a resolvable package or endpoint
- Exposes at least one tool, prompt or resource
- README has substantive content
- Includes a code example
- Documents its configuration
- Mentions credentials or security posture
- Last commit 3 days ago
- Has a release history
- Repository is not archived
- Licensed MIT
- Namespace verified in the official MCP registry
- Claimed by its owner
- Published under an organisation
- 6 tool(s) documented
- Provides prompt templates
- Provides resources
- 12 documented install method(s)
- Published to a package registry
- Offers a hosted endpoint — no local install
Histórico de versões
| Versões | Publicada |
|---|---|
| 1.0.1Mais recente | 14 de fev. de 2026 |