# mcp-schema-sentinel

> mcp-schema-sentinel — amurlaniakea-mcp-schema-sentinel. Use this tool when you need to detect potential security threats in your trusted tools, such as MCP tool-poisoning or rug-pull attacks, by monitoring schema and description changes. It provides read-only alerts when a trusted tool's configuration is modified silently, helping you identify and mitigate potential risks. Ideal for use in git-based workflows where tool integrity is crucial.

Canonical page: https://skillsregistry.net/skills/amurlaniakea-mcp-schema-sentinel  
JSON: https://api.skillsregistry.net/v1/skills/amurlaniakea-mcp-schema-sentinel

## Description

Read-only sensor that detects MCP tool-poisoning / rug-pull attacks:  alerts when a trusted tool's schema or description changes silently.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** AGPL-3.0
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/amurlaniakea/mcp-schema-sentinel)

## 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": "amurlaniakea-mcp-schema-sentinel"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/amurlaniakea-mcp-schema-sentinel` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/amurlaniakea-mcp-schema-sentinel/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