Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
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 promptscan https://promptscan.dev/mcp/~/.codex/config.toml
[mcp_servers.promptscan]
url = "https://promptscan.dev/mcp/"
# codex mcp add promptscan --url https://promptscan.dev/mcp/~/.cursor/mcp.json
{
"mcpServers": {
"promptscan": {
"url": "https://promptscan.dev/mcp/"
}
}
}.vscode/mcp.json
{
"servers": {
"promptscan": {
"type": "http",
"url": "https://promptscan.dev/mcp/"
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"promptscan": {
"httpUrl": "https://promptscan.dev/mcp/"
}
}
}claude_desktop_config.json · Customize › Connectors › Add custom connector
{
"mcpServers": {
"promptscan": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://promptscan.dev/mcp/"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"promptscan": {
"url": "https://promptscan.dev/mcp/"
}
}
}