# mcp-tool-poison-guard

> mcp-tool-poison-guard — princeruhulofficial-mcp-tool-poison-guard. Use this tool when you need to protect your system from malicious tool descriptions and schemas, as it detects and guards against tool poisoning and prompt injection attacks, providing risk scoring and safe rewriting capabilities. It solves problems related to security and data integrity, offering a secure interface for input validation and outputting audit reports. Ideal for use in high-risk environments where external API costs are a concern, it provides a reliable and cost-effective solution.

Canonical page: https://skillsregistry.net/skills/princeruhulofficial-mcp-tool-poison-guard  
JSON: https://api.skillsregistry.net/v1/skills/princeruhulofficial-mcp-tool-poison-guard

## Description

MCP server that detects and guards against tool poisoning and prompt injection attacks in tool descriptions and schemas. It provides risk scoring, pattern detection, safe rewriting, and audit reports with zero external API cost.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/lcxjkp6kp2)
- **Repository:** <https://github.com/princeruhulofficial/mcp-tool-poison-guard>

## 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": "princeruhulofficial-mcp-tool-poison-guard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/princeruhulofficial-mcp-tool-poison-guard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/princeruhulofficial-mcp-tool-poison-guard/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