MCP Percona Pg runs on your own machine — the client starts it, so there is no endpoint to ping. 78 installs a week from npm. Last commit 12 Oct 2026.
Manage Percona PostgreSQL + PgBouncer on Kubernetes — safe-by-default access modes and guards.
Today is the operative word: we check MCP Percona Pg every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-percona-pg -- npx -y @dockndevai/mcp-percona-pg
{
"mcpServers": {
"mcp-percona-pg": {
"args": [
"-y",
"@dockndevai/mcp-percona-pg"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-percona-pg]
command = "npx"
args = ["-y", "@dockndevai/mcp-percona-pg"]
{
"mcpServers": {
"mcp-percona-pg": {
"args": [
"-y",
"@dockndevai/mcp-percona-pg"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-percona-pg": {
"args": [
"-y",
"@dockndevai/mcp-percona-pg"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
KUBECONFIG_PATH (Path to a kube-config file that can reach the Percona Operator namespaces (empty = default resolution).), PERCONA_MODE (Access mode: read-only | read-write | admin.), PERCONA_NAMESPACE (Default namespace for PerconaPGCluster resources when a tool omits one.).
The author declared them in the registry entry; get the values from the project itself.
Safe, read-only-by-default MySQL, PostgreSQL & SQLite access for AI agents. TOON output.
Safety-railed database access: Postgres, MySQL, SQLite, Redis. Read-only by default.
Safety-railed database access for agents: Postgres, MySQL, Redis. Read-only by default.
PostgreSQL MCP wrapper with .env credential mapping, tool selection, and safe read-only defaults.
Fail-closed, read-only PostgreSQL and MongoDB access for AI agents over MCP.
EU-native PaaS for AI agents — deploy web apps with one sentence, managed Postgres, GDPR by default.
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log.
Answers built from our own checks of this server.