# Ask Human

> Use this tool when you need to escalate complex questions from AI agents to humans for authoritative input, preventing potential hallucinations and ensuring accurate decision-making. It solves problems in development workflows where AI assistants require human oversight on sensitive topics like database passwords or API endpoints. The tool takes AI questions as input, writes them to a markdown file, and outputs human-edited answers, providing a direct human-in-the-loop mechanism for reliable responses.

Canonical page: https://skillsregistry.net/skills/ask-human  
JSON: https://api.skillsregistry.net/v1/skills/ask-human

## Description

This MCP server enables AI agents to escalate questions to humans through a markdown file-based workflow, preventing hallucinations by providing a direct human-in-the-loop mechanism. Built by Mason Yarbrough for Kallro Inc. development workflows, it writes AI questions to a markdown file that humans edit with answers, using file watching to detect responses and return them to the AI agent. The implementation features cross-platform file locking, atomic operations, question timeout handling, file rotation for large logs, and robust markdown parsing, making it valuable for development scenarios where AI assistants need authoritative human input on decisions like database passwords, API endpoints, or architectural choices rather than generating potentially incorrect responses.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/ask-human)
- **Repository:** <https://github.com/masony817/ask-human-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": "ask-human"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ask-human` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ask-human/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