# mcp-guard

> Use this tool when you need to manage and control AI agent budgets, streamline approval workflows, and maintain detailed audit logs. It solves problems related to financial oversight, compliance, and accountability in AI agent interactions. The mcp-guard server takes input from AI agents like Claude Code, Cursor, and ChatGPT, and outputs controlled budget allocations, workflow approvals, and logged activity records.

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

## Description

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

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

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

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