mcp-guardian
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging level: DEBUG, INFO, WARN, ERROR | |
| NVD_API_KEY | No | NIST NVD API key for CVE lookups (20 req/min vs 5 without) | |
| METRICS_PORT | No | Metrics server port | |
| DASHBOARD_PORT | No | Dashboard HTTP port | |
| OPENAI_API_KEY | No | Optionally used by tiktoken for token counting | |
| METRICS_ENABLED | No | Enable Prometheus metrics endpoint | |
| DASHBOARD_ENABLED | No | Enable the dashboard server | |
| PRICING_OVERRIDES | No | Custom pricing JSON | |
| MCP_GUARDIAN_DB_PATH | No | Override SQLite database path |
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 | {} |
| logging | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_securityA | Scan MCP server configurations for security vulnerabilities (CVEs, auth, typo-squatting, secrets) |
| audit_costsB | Audit token usage and estimate costs per MCP server |
| check_healthB | Check health, latency, and reliability of MCP servers |
| full_reportA | Generate a complete security, cost, and health report for all MCP servers |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| audit-config | Generate security audit instructions for an MCP server config |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Latest Scan Report | Most recent security scan results across all MCP servers |
TDQS
Scored across 4 tools
Each tool targets a distinct concern: costs, security, health, and the aggregate report. full_report is the only overlapping tool, but it is clearly positioned as a consolidated view rather than a duplicate.
audit_costs, scan_security, and check_health follow a clear verb_noun pattern, but full_report breaks it by being a noun phrase instead of a verb-led action like generate_report. The pattern is still predictable and readable overall.
At four tools, the server is compact and well-scoped for MCP health, security, and cost oversight. Each tool earns its place by covering a distinct diagnostic dimension, with no redundant or extraneous operations.
The set covers security scanning, cost auditing, health checks, and a combined reporting path, giving agents the full diagnostic workflow for MCP server oversight. No obvious dead ends or required operations are absent.