# detect_slop_full

Detect slop patterns using both fast regex/NLP detectors and semantic LLM analysis via MCP sampling. Catches all 48 rules including subtle patterns like throat-clearing, grandiose stakes, and fractal summaries that regex cannot detect. Slower than detect_slop due to the sampling call.

Agent View of the PolicyLayer registry record for `detect_slop_full`. HTML page: https://policylayer.com/tools/0ju1c3-slop-cop/detect-slop-full

## Facts

- Tool: `detect_slop_full`
- Server: Slop Cop (`0ju1c3/slop-cop`) — https://policylayer.com/tools/0ju1c3-slop-cop.md
- Homepage: https://github.com/0ju1c3/slop-cop
- Risk category: Read (Low risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "detect_slop_full",
    "arguments": {}
  }
}
```

## Why detect_slop_full is rated Low

This tool retrieves and analyzes information about writing patterns without modifying data, executing code, destroying information, or making financial transactions. The 'full' variant simply uses both regex/NLP and semantic analysis methods to audit prose quality, making it a read-only analysis tool. The lower performance due to sampling calls does not change its fundamental Read category.

From the tool's own definition: "Tool description states it 'Detect[s] slop patterns' and performs 'analysis' via LLM sampling. The verb is purely analytical/detective with no modification, creation, deletion, or execution of external operations."

## Use case

AI agents call detect_slop_full to retrieve information from Slop Cop without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Slop Cop:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "detect_slop_full": {}
  }
}
```

## Other tools on Slop Cop (2)

- `fix_slop` — Destructive — https://policylayer.com/tools/0ju1c3-slop-cop/fix-slop.md
- `detect_slop` — Read — https://policylayer.com/tools/0ju1c3-slop-cop/detect-slop.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0ju1c3-slop-cop · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0ju1c3-slop-cop