loading…
Search for a command to run...
loading…
A transparent proxy and execution firewall that intercepts and audits AI agent tool calls against configurable security policies before forwarding them to downs
A transparent proxy and execution firewall that intercepts and audits AI agent tool calls against configurable security policies before forwarding them to downstream MCP servers. It provides safe execution environments with features like data redaction, anti-loop protection, and unified alert dispatching.
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"sovr-mcp-proxy": {
"command": "npx",
"args": []
}
}
}