# mcp-confirm

> mcp-confirm — les-k-mcp-confirm. Use this tool when you need to securely execute sensitive operations with human oversight, preventing unauthorized or malicious actions. It solves problems of prompt injection and unauthorized file access by sanitizing prompts and re-validating file paths. The mcp-confirm tool takes in sensitive tool calls and file paths as inputs, and outputs validated and confirmed actions, providing a secure interface for high-stakes operations.

Canonical page: https://skillsregistry.net/skills/les-k-mcp-confirm  
JSON: https://api.skillsregistry.net/v1/skills/les-k-mcp-confirm

## Description

MCP server that enforces single-use human confirmations for sensitive tool calls, sanitizes prompts against prompt injection, and re-validates file paths before destructive actions.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/xouoyarqye)
- **Repository:** <https://github.com/les-k/mcp-confirm>

## 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": "les-k-mcp-confirm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/les-k-mcp-confirm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/les-k-mcp-confirm/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