# agent-guard-mcp

> agent-guard-mcp — dygogogo-agent-guard-mcp. Use this tool when you need to manage and control AI agent budgets, implement approval workflows, and track audit logs for agents like Claude Code, Cursor, and ChatGPT. It provides a centralized server for monitoring and regulating AI agent activities, ensuring transparency and accountability. Ideal for use cases requiring robust budget control and compliance tracking, with integration capabilities via git.

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

## Description

MCP Guard Server - Budget control, approval workflows and audit logging for AI agents (Claude Code, Cursor, ChatGPT)

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/dygogogo/agent-guard-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": "dygogogo-agent-guard-mcp"
    }
  }
}
```

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