# cyclops

> cyclops — enchanter-ai-cyclops. Use this tool when you need to prevent data exfiltration between AI agents and their tools, as it monitors and blocks toxic flows from untrusted sources to sensitive data and egress points. The cyclops security proxy detects and blocks these flows deterministically, without relying on large language models (LLMs). Ideal for use cases requiring robust security and data protection, cyclops ensures the integrity of sensitive information.

Canonical page: https://skillsregistry.net/skills/enchanter-ai-cyclops  
JSON: https://api.skillsregistry.net/v1/skills/enchanter-ai-cyclops

## Description

A security MCP proxy that monitors and blocks data exfiltration between AI agents and their tools by detecting toxic flows (untrusted → sensitive → egress) deterministically with zero LLM calls in the decision path.

## Trust

- **Trust score (0–1):** 0.67
- **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/u6pkcp9863)
- **Repository:** <https://github.com/enchanter-ai/cyclops>

## 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": "enchanter-ai-cyclops"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/enchanter-ai-cyclops` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/enchanter-ai-cyclops/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