# crossfire-mcp

> Use this tool when you need to stress-test your decisions with adversarial AI debate, solving problems of confirmation bias and weak argumentation. It takes in a decision or argument as input and outputs a skeptical analysis, using web-search grounded information to challenge assumptions. Ideal for use cases where critical thinking and robust decision-making are crucial, such as policy-making, research, or strategic planning.

Canonical page: https://skillsregistry.net/skills/grzesir-crossfire-mcp  
JSON: https://api.skillsregistry.net/v1/skills/grzesir-crossfire-mcp

## Description

Stress-test your decisions with adversarial AI debate. MCP server for Claude Code. Skeptic vs Steelman, web-search grounded, confirmation bias attack.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** search
- **Updated:** 2026-04-22

## Source

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

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