# Vigile

> Use this tool when you need to protect your MCP servers and agent skills from security threats, such as tool poisoning and data exfiltration. Vigile provides comprehensive security scanning and trust scoring, detecting attacks across multiple platforms, including npm, Smithery, and PyPI, and agent skills from Claude Code, Cursor, and OpenClaw. It offers a 0-100 trust score for each server and skill, helping you identify and mitigate potential risks.

Canonical page: https://skillsregistry.net/skills/vigile  
JSON: https://api.skillsregistry.net/v1/skills/vigile

## Description

Vigile provides security scanning and trust scoring for MCP servers and agent skills. It detects tool poisoning, data exfiltration, prompt injection, and supply chain attacks across servers from npm, Smithery, and PyPI, plus agent skills from Claude Code, Cursor, and OpenClaw. Each server and skill receives a 0-100 trust score, and the platform covers 54 detection rules across seven platforms.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

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

## 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": "vigile"
    }
  }
}
```

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