One private memory across Claude, ChatGPT, Cursor, and every MCP client — on-device, zero-knowledge. Plaintext never leaves your machine.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add sovseal-memory -- npx -y @sovseal/mcp-server~/.codex/config.toml
[mcp_servers.sovseal-memory]
command = "npx"
args = ["-y", "@sovseal/mcp-server"]
# codex mcp add sovseal-memory -- npx -y @sovseal/mcp-server~/.cursor/mcp.json
{
"mcpServers": {
"sovseal-memory": {
"command": "npx",
"args": [
"-y",
"@sovseal/mcp-server"
]
}
}
}.vscode/mcp.json
{
"servers": {
"sovseal-memory": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@sovseal/mcp-server"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"sovseal-memory": {
"command": "npx",
"args": [
"-y",
"@sovseal/mcp-server"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"sovseal-memory": {
"command": "npx",
"args": [
"-y",
"@sovseal/mcp-server"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"sovseal-memory": {
"command": "npx",
"args": [
"-y",
"@sovseal/mcp-server"
]
}
}
}