Read-only Wazuh SIEM/XDR control CLI with an MCP adapter
Read-only Wazuh SIEM/XDR control CLI with an MCP adapter. The wazuh mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.
An MCP server that lets an AI client query your Wazuh SIEM/XDR: alerts, agents, vulnerabilities, rules, and more, read-only.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Everything the assistant can do here goes through one of these:
list_agents — List all agents with optional status filtering (active, disconnected, never_connected, pending)get_agent — Get detailed info for a specific agent by IDget_agent_stats — Get CPU, memory, and disk statistics for an agentget_alerts — Retrieve recent alerts with filtering by time range, level, agent, rule, and text searchget_alert — Retrieve a single alert by IDsearch_alerts — Full-text search across alerts with optional time range filteringlist_vulnerabilities — List vulnerability inventory with optional CVE, agent, severity, and package filterssearch_vulnerabilities — Search vulnerability inventory by CVE, package, agent, or descriptionlist_rules — List detection rules with level and group filteringget_rule — Get full rule details including compliance mappingssearch_rules — Search rules by description textget_sca_policies — List SCA policies and scores for an agent (CIS benchmarks, etc.)You will need 7 environment variables: WAZUH_URL, WAZUH_USERNAME, WAZUH_PASSWORD, WAZUH_INDEXER_URL, WAZUH_INDEXER_USERNAME, WAZUH_INDEXER_PASSWORD, WAZUH_BASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Wazuh's toolset — list_agents, get_agent, get_agent_stats and 11 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| list_agents | List all agents with optional status filtering (active, disconnected, never_connected, pending) |
| get_agent | Get detailed info for a specific agent by ID |
| get_agent_stats | Get CPU, memory, and disk statistics for an agent |
| get_alerts | Retrieve recent alerts with filtering by time range, level, agent, rule, and text search |
| get_alert | Retrieve a single alert by ID |
| search_alerts | Full-text search across alerts with optional time range filtering |
| list_vulnerabilities | List vulnerability inventory with optional CVE, agent, severity, and package filters |
| search_vulnerabilities | Search vulnerability inventory by CVE, package, agent, or description |
| list_rules | List detection rules with level and group filtering |
| get_rule | Get full rule details including compliance mappings |
| search_rules | Search rules by description text |
| get_sca_policies | List SCA policies and scores for an agent (CIS benchmarks, etc.) |
| get_sca_checks | Get individual check results with remediation steps and compliance mappings |
| get_agent_os | Get OS information (name, version, architecture, hostname) |
{
"mcpServers": {
"wazuh-1": {
"command": "npx",
"args": ["-y", "invocation"],
"env": {
"WAZUH_URL": "your-value",
"WAZUH_USERNAME": "your-value",
"WAZUH_PASSWORD": "your-value",
"WAZUH_INDEXER_URL": "your-value",
"WAZUH_INDEXER_USERNAME": "your-value",
"WAZUH_INDEXER_PASSWORD": "your-value",
"WAZUH_BASE_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| WAZUH_URL | Endpoint or connection string the server talks to. | Yes |
| WAZUH_USERNAME | Configuration value read at startup. | Optional |
| WAZUH_PASSWORD | Configuration value read at startup. | Optional |
| WAZUH_INDEXER_URL | Endpoint or connection string the server talks to. | Yes |
| WAZUH_INDEXER_USERNAME | Configuration value read at startup. | Optional |
| WAZUH_INDEXER_PASSWORD | Configuration value read at startup. | Optional |
| WAZUH_BASE_URL | Endpoint or connection string the server talks to. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.