# Thoth

> Use this tool when you need to enforce compliance and security policies for AI agents in real-time, intercepting and blocking non-compliant actions across various deployments. Thoth provides fleet-wide visibility and ships with pre-built policy packs for major regulatory frameworks, such as HIPAA, GDPR, and SOC 2. It integrates with popular AI platforms and offers a developer SDK for customized instrumentation.

Canonical page: https://skillsregistry.net/skills/atensecurity-thoth  
JSON: https://api.skillsregistry.net/v1/skills/atensecurity-thoth

## Description

Thoth is Aten Security's runtime enforcement platform for AI agents, operating as an MCP proxy that intercepts tool calls before execution. It blocks non-compliant actions in under 100ms, provides fleet-wide visibility across Claude Desktop, Cursor, and API deployments, and ships pre-built compliance policy packs for HIPAA, SOC 2, EU AI Act, GDPR, NIST, and OWASP. Includes a developer SDK for LangChain, CrewAI, and Anthropic SDK instrumentation. Aten Security holds SOC 2 Type I and II certifications.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/atensecurity-thoth)
- **Repository:** <https://github.com/atensecurity/thoth>

## 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": "atensecurity-thoth"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/atensecurity-thoth` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/atensecurity-thoth/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