AI Agent Guardrails MCP server - security layer
[!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.
| 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 |
npm install
{
"mcpServers": {
"guardrails": {
"type": "stdio",
"command": "node",
"args": ["/path/to/guardrails-mcp-server/index.js"]
}
}
}
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
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
npx -y guardrails-mcp-serverMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-expertvagabond-guardrails": {
"command": "npx",
"args": [
"-y",
"guardrails-mcp-server"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup referenceguardrails-mcp-servernpmio.github.ExpertVagabond/guardrails works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.