# Arcjet MCP

> Use this tool when you need to secure your AI code and protect against threats such as prompt injection and bot attacks. The Arcjet MCP platform provides a runtime security solution that enforces budgets, detects bots, and shields personal information, with features like rate limiting and filters. It integrates with popular coding tools like VS Code, ChatGPT, and Claude Code, allowing for seamless security management and verification.

Canonical page: https://skillsregistry.net/skills/arcjet-arcjet-mcp  
JSON: https://api.skillsregistry.net/v1/skills/arcjet-arcjet-mcp

## Description

Arcjet is the runtime security platform that ships with your AI code. Enforce budgets, stop prompt injection, detect bots, and protect personal information with Arcjet's AI security building blocks.

With the Arcjet MCP server, your coding agent can create sites, configure remote rules (rate limiting, bot protection, shield, filters), inspect requests, explain decisions, and manage security posture via MCP. DRY_RUN → verify → promote workflow built in. Works with Claude Code, Cursor, VS Code/Copilot, ChatGPT, Windsurf.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-13

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/arcjet/arcjet-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": "arcjet-arcjet-mcp"
    }
  }
}
```

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