# Heimdall

> Heimdall — 2alf-heimdall. Use this tool when you need to ensure the integrity and authenticity of MCP config and server files loaded by local AI agents. Heimdall solves the problem of detecting unauthorized modifications or tampering with critical configuration files, providing a tamper-evident integrity monitor. It takes git-versioned files as input and outputs alerts or notifications in case of discrepancies, making it ideal for use in secure and compliant AI agent deployments.

Canonical page: https://skillsregistry.net/skills/2alf-heimdall  
JSON: https://api.skillsregistry.net/v1/skills/2alf-heimdall

## Description

Tamper-evident integrity monitor for the MCP config & server files your local AI agents load.

## Trust

- **Trust score (0–1):** 0.51
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** GPL-3.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/2alf/Heimdall)

## 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": "2alf-heimdall"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/2alf-heimdall` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/2alf-heimdall/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