# mcp-on-demand-tools

> mcp-on-demand-tools — aarongoldsmith-mcp-on-demand-tools. Use this tool when you need to analyze and understand the potential actions of an AI agent in a given scenario. It solves problems related to debugging and testing agent behavior by simulating tool calls and providing insights into what the agent would have done under different circumstances. The tool takes in hypothetical scenarios as input and outputs a log of intended actions, allowing for evaluation and refinement of agent decision-making processes.

Canonical page: https://skillsregistry.net/skills/aarongoldsmith-mcp-on-demand-tools  
JSON: https://api.skillsregistry.net/v1/skills/aarongoldsmith-mcp-on-demand-tools

## Description

Intentionally hallucinated tool calls: See what your agent would have done if it had the chance.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/AaronGoldsmith/mcp-on-demand-tools)

## 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": "aarongoldsmith-mcp-on-demand-tools"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/aarongoldsmith-mcp-on-demand-tools` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/aarongoldsmith-mcp-on-demand-tools/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