Self-hosted governance layer between AI assistants and your real data. Deterministic PII masking, allow/deny policy, hash-chained audit, offline-verifiable Ed25519 receipts per access when a receipt sink is configured, coverage reconciliation against the DB's own query counters to surface gateway…
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add conarium -- npx -y @conarium-ai/core~/.codex/config.toml
[mcp_servers.conarium]
command = "npx"
args = ["-y", "@conarium-ai/core"]
# codex mcp add conarium -- npx -y @conarium-ai/core~/.cursor/mcp.json
{
"mcpServers": {
"conarium": {
"command": "npx",
"args": [
"-y",
"@conarium-ai/core"
]
}
}
}.vscode/mcp.json
{
"servers": {
"conarium": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@conarium-ai/core"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"conarium": {
"command": "npx",
"args": [
"-y",
"@conarium-ai/core"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"conarium": {
"command": "npx",
"args": [
"-y",
"@conarium-ai/core"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"conarium": {
"command": "npx",
"args": [
"-y",
"@conarium-ai/core"
]
}
}
}