# agentguard-mcp

> agentguard-mcp — mukundakatta-agentguard-mcp. Use this tool when you need to secure agent tools with a declarative network-egress firewall, solving problems of unauthorized outgoing traffic and enhancing security for Git-based projects. It takes in configuration inputs and outputs a wrapped, secure agent tool, providing a robust interface for network traffic control. Ideal for use cases requiring strict network access control and security in development environments.

Canonical page: https://skillsregistry.net/skills/mukundakatta-agentguard-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mukundakatta-agentguard-mcp

## Description

MCP server: declarative network-egress firewall for agent tools. Wraps @mukundakatta/agentguard.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

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

## Source

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

## 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": "mukundakatta-agentguard-mcp"
    }
  }
}
```

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