mcp-keycloak
Enables MCP-capable clients to inspect and manage Keycloak realms, users, clients, roles, and groups with layered security modes, realm allowlisting, protected realms, delete gating, dry-run, and audit logging.
README
mcp-keycloak
A Model Context Protocol server for Keycloak. It lets an MCP-capable client (Claude Desktop, Claude Code, etc.) inspect and manage Keycloak realms, users, clients, roles, and groups — with security controlled entirely by flags.
The design goal is safe by default: it starts read-only, scopes to an allowlist of realms, protects sensitive realms from mutation, and gates destructive operations behind an explicit opt-in.
Features
- Multi-realm — every tool takes a
realmargument; scope it with an allowlist. - Access modes —
read-only→read-write→admin, layered so a mode never exposes tools above its level. - Security flags — realm allowlist, protected realms, delete gating, dry-run, and JSON audit logging (see below).
- Two auth strategies — confidential-client service account (recommended) or admin username/password.
- Zero heavy dependencies — a thin fetch-based Admin REST client, plus the MCP SDK and zod.
Security model
| Concern | Flag | Default | Effect |
|---|---|---|---|
| What can the server do at all? | KEYCLOAK_MODE |
read-only |
read-only exposes only read tools; read-write adds mutations; admin adds destructive tools. Tools above the mode are never registered. |
| Which realms are in scope? | KEYCLOAK_REALM_ALLOWLIST |
(all) | Comma-separated. When set, any operation on a realm outside the list is refused. |
| Which realms are read-only forever? | KEYCLOAK_PROTECTED_REALMS |
master |
Protected realms can be read but never mutated or deleted, regardless of mode. |
| Can it delete? | KEYCLOAK_ALLOW_DELETE |
false |
delete_* tools require this and admin mode. |
| Preview without touching Keycloak | KEYCLOAK_DRY_RUN |
false |
Write/admin tools validate + log intent, then return without calling Keycloak. |
| Audit trail | KEYCLOAK_AUDIT_LOG |
true |
Emits a JSON line to stderr per guarded operation (ALLOW / DENY / DRY_RUN). |
These layers are independent — for example admin mode with KEYCLOAK_ALLOW_DELETE=false can create and update users but cannot delete them.
Tools
Read (read-only+): list_realms, get_realm, list_users, get_user, count_users, list_clients, list_realm_roles, list_groups
Write (read-write+): create_user, update_user, reset_password, logout_user
Admin (admin): delete_user
Quickstart — add to your agent
Published on npm as @dockndevai/mcp-keycloak. No clone or build needed — your MCP client runs it on demand with npx. Start in read-only mode; see .env.example for every variable and docs/CLIENTS.md for the full per-client guide.
Claude Code (CLI)
claude mcp add keycloak -e KEYCLOAK_URL="https://keycloak.example.com" -e KEYCLOAK_CLIENT_ID="admin-cli" -e KEYCLOAK_CLIENT_SECRET="your-secret" -e KEYCLOAK_MODE="read-only" -- npx -y @dockndevai/mcp-keycloak
Claude Desktop · Cursor · Windsurf — same block in claude_desktop_config.json, .cursor/mcp.json, or ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"keycloak": {
"command": "npx",
"args": [
"-y",
"@dockndevai/mcp-keycloak"
],
"env": {
"KEYCLOAK_URL": "https://keycloak.example.com",
"KEYCLOAK_CLIENT_ID": "admin-cli",
"KEYCLOAK_CLIENT_SECRET": "your-secret",
"KEYCLOAK_MODE": "read-only"
}
}
}
}
OpenAI Codex CLI — in ~/.codex/config.toml:
[mcp_servers.keycloak]
command = "npx"
args = ["-y", "@dockndevai/mcp-keycloak"]
env = { KEYCLOAK_URL = "https://keycloak.example.com", KEYCLOAK_CLIENT_ID = "admin-cli", KEYCLOAK_CLIENT_SECRET = "your-secret", KEYCLOAK_MODE = "read-only" }
VS Code (GitHub Copilot, Agent mode) — in .vscode/mcp.json:
{
"servers": {
"keycloak": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@dockndevai/mcp-keycloak"
],
"env": {
"KEYCLOAK_URL": "https://keycloak.example.com",
"KEYCLOAK_CLIENT_ID": "admin-cli",
"KEYCLOAK_CLIENT_SECRET": "your-secret",
"KEYCLOAK_MODE": "read-only"
}
}
}
}
Configure
Copy .env.example and fill it in, or set the variables directly in your MCP client config. A confidential client with the realm-management roles you need is the recommended credential.
Run from source (development)
Prefer the published package above. To run from a clone:
npm install
npm run build
node dist/index.js # with the environment variables set
Develop
npm run dev # watch mode
npm test # unit tests for the security policy
npm run typecheck
Publishing
This server ships a server.json for the official MCP registry and an mcpName for npm ownership validation. See PUBLISHING.md for publishing to npm and listing on the MCP registry, Smithery, Glama, Cursor, and PulseMCP.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.