# arc-security

> arc-security, an MCP server by arcself.com, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Scan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings.

- Canonical: https://www.anchorterminal.com/tools/arcself-arc-security
- Markdown: https://www.anchorterminal.com/tools/arcself-arc-security.md (~450 tokens)
- Slim: https://www.anchorterminal.com/tools/arcself-arc-security.min.md (~380 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/arcself-arc-security.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

# arc-security

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by arcself.com (https://arcself.com)
- Category: Observability & incidents (https://www.anchorterminal.com/categories/observability.md)
- Listed because: It's published in the registry under arcself.com, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Scan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings.

## Facts

- MCP registry: `com.arcself/arc-security` 0.5.1
- Package: npm `arc-security-mcp` (stdio)
- Source: https://github.com/ArcSelf/arc-security-mcp
- npm downloads a week: 72
- Registry entry updated: 2026-02-17

- JSON: https://www.anchorterminal.com/api/v1/tools/arcself-arc-security.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming