# mcp-guard

> mcp-guard — njengah-mcp-guard. Use this tool when you need to secure and govern access to sensitive systems and tools, such as source control and production APIs, with features like approvals and audit trails. It provides a command-line interface for managing MCP tool calls, ensuring local-first security and compliance. Ideal for use cases where sensitive data and systems require strict access controls and auditing.

Canonical page: https://skillsregistry.net/skills/njengah-mcp-guard  
JSON: https://api.skillsregistry.net/v1/skills/njengah-mcp-guard

## Description

Local-first CLI for MCP tool governance: allow/block/approve policies, audit reports. Not a live gateway.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/Njengah/mcp-guard)

## 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": "njengah-mcp-guard"
    }
  }
}
```

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