# cco-mcp

> Use this tool when you need to monitor and control AI agent actions in real-time, ensuring transparency and accountability in Claude Code tool usage. The cco-mcp system provides a web dashboard for auditing and approving tool calls, solving problems related to unauthorized or malicious AI activity. It accepts tool call inputs and outputs approval decisions, ideal for use cases requiring strict oversight and governance of AI agent behavior.

Canonical page: https://skillsregistry.net/skills/toolprint-cco-mcp  
JSON: https://api.skillsregistry.net/v1/skills/toolprint-cco-mcp

## Description

Real-time audit and approval system for Claude Code tool calls, enabling monitoring and control of AI agent actions with a web dashboard.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/wsvpgvuszw)
- **Repository:** <https://github.com/toolprint/cco-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": "toolprint-cco-mcp"
    }
  }
}
```

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