GuardRail MCP v2.0 (Enterprise)
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GUARDRAIL_ENTERPRISE | No | Set to '1' to enable enterprise features (RBAC, policy packs, audit logs, etc.) | |
| GUARDRAIL_HTTP_API_KEY | No | API key required when running in HTTP mode for authentication | |
| GUARDRAIL_ENTERPRISE_CONFIG | No | Path to the enterprise configuration JSON file |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| audit_code_safetyA | Hybrid multi-engine scan: secrets regex, Python AST + advanced multi-hop taint, tree-sitter structural sinks, language grids, custom rules/plugins. Returns redacted issues, engines used, risk score, security_verdict. |
| audit_cloud_costC | Rough AWS/GCP monthly SKU catalog estimate from IaC text. |
| audit_infra_securityC | IaC misconfigs + budget gate on estimated monthly burn. |
| scan_repositoryB | Parallel recursive repo scan with optional incremental cache. |
| scan_git_diffB | Scan only files changed in a git range (PR/diff) or staged changes. |
| scan_dependenciesC | Dependency inventory + optional OSV CVE query. |
| export_sarifC | Convert issues to SARIF 2.1.0 JSON. |
| generate_sbomC | Generate CycloneDX and/or SPDX SBOM JSON. |
| suggest_fixesC | Template or LLM-assisted fix drafts for findings (never auto-applied). |
| audit_container_configD | Dockerfile / Kubernetes security heuristics. |
| full_pipelineD | Repo/diff scan + deps + fixes + SARIF + SBOM. |
| list_pluginsA | List loaded plugins and custom rule counts. |
| engine_statusB | Report hybrid engine capabilities (tree-sitter langs, plugins, etc.). |
| security_scoreC | Compute security score/grade from an issues list and optionally record history. |
| scan_historyC | Return recent dashboard scan history from local SQLite. |
| enterprise_healthC | Enterprise health, metrics, and non-secret config status. |
| enterprise_policy_statusB | Show active policy pack and gate thresholds for the caller tenant. |
| evaluate_policyC | Run policy pack evaluation against a prior scan result object. |
| compliance_reportC | Generate a lightweight compliance evidence report for auditors. |
| list_audit_eventsC | List recent in-memory audit events (operator+). |
| issue_access_tokenC | Issue a short-lived JWT (admin). Requires GUARDRAIL_JWT_SECRET. |
| reload_enterprise_configC | Reload enterprise YAML/JSON from disk (admin). |
| manage_tenantC | Inspect or update in-memory tenant quota counters (admin). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 23 tools
Each tool has a distinct domain (cloud cost, code safety, container, infra, compliance, etc.), but some overlap exists between audit functions (e.g., audit_code_safety vs. audit_infra_security) which could cause confusion. Descriptions are clear enough to differentiate in most cases.
Most tools follow a consistent verb_noun pattern with underscores (e.g., audit_cloud_cost, scan_repository). A few tools like 'full_pipeline' and 'enterprise_health' break the pattern but are still readable. Overall consistent.
23 tools is on the high side for a single server, but each serves a specific purpose in a comprehensive security scanning and management suite. The count feels justified given the breadth of functionality.
The tool set covers scanning, auditing, compliance, reporting, policy management, and admin tasks. Minor gaps exist (e.g., no tool to delete scan history or manage users beyond tenants), but core workflows are complete.