# Prompt Suppressor (MCP)

> Use this tool when you need to enforce clean prompt structures and prevent model-invented instructions from propagating through your system. It solves problems related to capability hallucinations and ensures reliable input/output interfaces by stripping unwanted instructions. Ideal for use cases where precise control over model inputs is crucial, such as in high-stakes AI applications.

Canonical page: https://skillsregistry.net/skills/steveswain14-mcp-prompt-suppressor  
JSON: https://api.skillsregistry.net/v1/skills/steveswain14-mcp-prompt-suppressor

## Description

A standalone MCP server that enforces clean prompt structure, strips model‑invented instructions, and detects capability hallucinations before they propagate through your system.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/uowkduog3j)
- **Repository:** <https://github.com/steveswain14/mcp-prompt-suppressor>

## 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": "steveswain14-mcp-prompt-suppressor"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/steveswain14-mcp-prompt-suppressor` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/steveswain14-mcp-prompt-suppressor/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