# io.github.MukundaKatta/agentguard

> Use this tool when you need to enforce network security policies for agent tools by controlling outgoing traffic. It checks URLs against a declarative policy, helping to prevent unauthorized access and data breaches. Ideal for use cases where agent tools require internet access, providing a secure and controlled environment with customizable policy inputs and alert outputs.

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

## Description

Network-egress firewall for agent tools: check URLs against a declarative policy.

## Trust

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

## Facts

- **Version:** 0.1.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-09-19

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.MukundaKatta%2Fagentguard)
- **Repository:** <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": "io-github-mukundakatta-agentguard"
    }
  }
}
```

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