AI Access Proxy Layer — granular permission gateway for AI agents. Connect services, define scopes, get an MCP endpoint.
接入配置
选择客户端，复制配置，再按项目文档补齐环境变量。
claude mcp add --transport http scopegate 'https://scopegate.dev/api/mcp/<API_KEY>'~/.codex/config.toml
[mcp_servers.scopegate]
url = "https://scopegate.dev/api/mcp/<API_KEY>"
# codex mcp add scopegate --url 'https://scopegate.dev/api/mcp/<API_KEY>'~/.cursor/mcp.json
{
"mcpServers": {
"scopegate": {
"url": "https://scopegate.dev/api/mcp/<API_KEY>"
}
}
}.vscode/mcp.json
{
"servers": {
"scopegate": {
"type": "http",
"url": "https://scopegate.dev/api/mcp/<API_KEY>"
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"scopegate": {
"httpUrl": "https://scopegate.dev/api/mcp/<API_KEY>"
}
}
}claude_desktop_config.json · Customize › Connectors › Add custom connector
{
"mcpServers": {
"scopegate": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://scopegate.dev/api/mcp/<API_KEY>"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"scopegate": {
"url": "https://scopegate.dev/api/mcp/<API_KEY>"
}
}
}