Add a responsible-AI safety layer to any agent in one URL. Remote MCP server: 8-dimension evaluation, prompt-injection detection, tool-call gating, PII scanning, and India DPDP compliance.
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 rail-score https://mcp.responsibleailabs.ai/mcp~/.codex/config.toml
[mcp_servers.rail-score]
url = "https://mcp.responsibleailabs.ai/mcp"
# codex mcp add rail-score --url https://mcp.responsibleailabs.ai/mcp~/.cursor/mcp.json
{
"mcpServers": {
"rail-score": {
"url": "https://mcp.responsibleailabs.ai/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"rail-score": {
"type": "http",
"url": "https://mcp.responsibleailabs.ai/mcp"
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"rail-score": {
"httpUrl": "https://mcp.responsibleailabs.ai/mcp"
}
}
}claude_desktop_config.json · Customize › Connectors › Add custom connector
{
"mcpServers": {
"rail-score": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.responsibleailabs.ai/mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"rail-score": {
"url": "https://mcp.responsibleailabs.ai/mcp"
}
}
}