MCP Keycloak runs on your own machine — the client starts it, so there is no endpoint to ping. 366 installs a week from npm. Last commit 30 Aug 2026.
Keycloak admin for AI agents — realms, users, clients, roles; safe-by-default governance.
Today is the operative word: we check MCP Keycloak 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-keycloak -- npx -y @dockndevai/mcp-keycloak
{
"mcpServers": {
"mcp-keycloak": {
"args": [
"-y",
"@dockndevai/mcp-keycloak"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-keycloak]
command = "npx"
args = ["-y", "@dockndevai/mcp-keycloak"]
{
"mcpServers": {
"mcp-keycloak": {
"args": [
"-y",
"@dockndevai/mcp-keycloak"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-keycloak": {
"args": [
"-y",
"@dockndevai/mcp-keycloak"
],
"command": "npx"
}
}
}
Administer Keycloak via its Admin REST API: users, roles, clients, groups, IdP, events.
Safe Google Workspace admin for AI agents: read-only by default, confirm-gated deletes, audit log.
Governance for LLM agents: 7 enforced rules + read-only reference tools. Safe in any MCP client.
API governance for AI agents. Detects breaking changes, scores blast radius, blocks unsafe calls.
Kubernetes monitoring & ops for AI agents — safe-by-default access modes and guards.
Managed Keycloak from any MCP client: clusters, realms, apps, SSO, users, domains, audit events.
Safe scheduled AI agents with governance gates. Verified, receipted, fail-closed.
Safe Kubernetes access for AI agents via MCP. Read-only by default, with explicit permission modes.
Answers built from our own checks of this server.