Skip to content

Arcjet MCP server

The Arcjet MCP server lets AI assistants access your Arcjet account through the Model Context Protocol (MCP), an open standard for connecting AI tools to external services.

Connect your AI coding tools to Arcjet to:

  • List teams you belong to.
  • List sites within a team.
  • Create new sites within a team.
  • Get site keys (ARCJET_KEY) for use in your projects.
  • List requests received by a site with optional filtering.
  • Get request details including headers, rules executed, and decision info.
  • Get site quota usage and limits for the current billing window.

The MCP server is available at:

https://api.arcjet.com/mcp

It implements the latest MCP Authorization and Streamable HTTP specifications with OAuth-based authentication.

Any client that supports the latest MCP specification with Streamable HTTP transport and OAuth authorization is supported. This includes:

  1. In ChatGPT, go to Settings.
  2. Navigate to Connectors and select Add connection.
  3. Enter https://api.arcjet.com/mcp as the server URL.
  4. Select OAuth for authentication.
  5. Click Create.

ChatGPT handles the OAuth flow automatically.

Terminal window
claude mcp add arcjet --transport http https://api.arcjet.com/mcp

Claude Code will open a browser for OAuth authentication on first connection. Once authenticated, you can use the /mcp command to verify the connection.

  1. Open Settings in the sidebar.
  2. Navigate to Connectors and select Add custom connector.
  3. Configure the connector:
    • Name: Arcjet
    • URL: https://api.arcjet.com/mcp

Add to .cursor/mcp.json in your project:

{
"mcpServers": {
"arcjet": {
"type": "streamable-http",
"url": "https://api.arcjet.com/mcp"
}
}
}

After adding the server, Cursor will show a Needs login prompt. Click it to authorize Cursor to access your Arcjet account.

Add to your .vscode/mcp.json in your project or user settings:

{
"servers": {
"arcjet": {
"type": "http",
"url": "https://api.arcjet.com/mcp"
}
}
}

Or add it via the command palette:

  1. Open the Command Palette (Ctrl+Shift+P on Windows/Linux or Cmd+Shift+P on macOS).
  2. Run MCP: Add Server.
  3. Select HTTP.
  4. Enter the URL: https://api.arcjet.com/mcp
  5. Enter the name: Arcjet
  6. Select Workspace or User depending on your preference.

VS Code will prompt you to authenticate via OAuth on first use.

Add to your mcp_config.json file:

{
"mcpServers": {
"arcjet": {
"serverUrl": "https://api.arcjet.com/mcp"
}
}
}

For more details, see the Windsurf MCP documentation.

Once connected, the following tools are available to your AI assistant:

ToolDescription
list-teamsLists teams the authenticated user belongs to.
list-sitesLists sites within a specified team.
create-siteCreates a new site within a specified team.
get-site-keyReturns the SDK key (ARCJET_KEY) for a specific site.
list-requestsLists recent requests for a site. Supports filtering by conclusion (ALLOW, DENY, ERROR) and pagination.
get-request-detailsReturns full details for a specific request including headers, rules executed, and decision information.
get-site-quotaReturns quota usage and limits for a site in the current billing window.

The MCP server uses OAuth for authentication. When you first connect from any supported client, you will be redirected to sign in with your Arcjet account. Once authenticated, your AI assistant can securely access your account resources.

  • Verify the endpoint — always confirm you are connecting to https://api.arcjet.com/mcp.
  • Review tool calls — enable confirmation prompts in your AI client so you can review actions before they execute.
  • Trusted clients only — only connect from AI clients you trust. Connecting grants the AI tool the same access as your Arcjet account.

Discussion