# mcp-guardian

> Use this tool when you need to enforce security policies, monitor server health, and track costs in MCP infrastructure. It solves problems related to security governance, cost management, and system health by providing features like YAML-configurable policies, real-time monitoring, and OAuth 2.1/OIDC authentication. It takes YAML configurations and JSON-RPC probes as inputs and outputs tracked costs, server health status, and security policy enforcement via a web dashboard.

Canonical page: https://skillsregistry.net/skills/rudraneel93-mcp-guardian  
JSON: https://api.skillsregistry.net/v1/skills/rudraneel93-mcp-guardian

## Description

Security, cost, and health governance proxy for MCP infrastructure. Enforces YAML-configurable security policies (blocklists, rate limits, token budgets), tracks real token costs via tiktoken, monitors server health with live JSON-RPC probes. Features OAuth 2.1/OIDC with RBAC, web dashboard, payload normalization, semantic shell AST analysis, mTLS, and a formal STRIDE threat model.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** social-media
- **Updated:** 2026-05-13

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/quqcjsd6e9)
- **Repository:** <https://github.com/rudraneel93/mcp-guardian>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "rudraneel93-mcp-guardian"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rudraneel93-mcp-guardian` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rudraneel93-mcp-guardian/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt