Wazuh MCP Server
by INFOKOM-KI
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Host to bind for streamable_http transport (e.g., 0.0.0.0). Default loopback. | |
| MCP_PORT | No | Port to bind for streamable_http transport. | |
| MCP_API_KEY | No | Pre-shared API key for streamable_http transport. Required when binding beyond 127.0.0.1. Format: btm_<43-char-urlsafe-base64>. | |
| NVD_API_KEY | No | Optional API key for NVD CVE lookups; raises rate limits. | |
| OTX_API_KEY | No | API key for AlienVault OTX threat intelligence. Optional. | |
| GITHUB_TOKEN | No | Optional GitHub token for CVE PoC lookups; raises rate limits. | |
| RAPIDAPI_KEY | No | API key for RapidAPI lookups. Optional. | |
| ARGUS_API_KEY | No | API key for Argus threat intelligence. Optional. | |
| MCP_TRANSPORT | No | Transport mode: 'stdio' (default) or 'streamable_http'. | stdio |
| NETRA_API_KEY | No | API key for Netra threat intelligence. Optional. | |
| WAZUH_API_URL | No | The URL of the Wazuh Manager API (port 55000). Optional; enables Manager API tools. | |
| URLAUS_API_KEY | No | API key for URLhaus threat intelligence. Optional. | |
| WAZUH_API_USER | No | The username for the Wazuh Manager API. Required if WAZUH_API_URL is set. | |
| WAZUH_READ_ONLY | No | If 'true', disables destructive tools. Default is read-only. | |
| CROWDSEC_API_KEY | No | API key for CrowdSec threat intelligence. Optional; tools degrade gracefully without it. | |
| ABUSEIPDB_API_KEY | No | API key for AbuseIPDB threat intelligence. Optional. | |
| THREATFOX_API_KEY | No | API key for ThreatFox threat intelligence. Optional. | |
| WAZUH_INDEXER_URL | Yes | The URL of the Wazuh Indexer (OpenSearch, port 9200). Required for core alert/event data. | |
| BLUETEAM_AUDIT_LOG | No | Path to a JSONL audit trail file (optional). | |
| BLUETEAM_CMDB_FILE | No | Path to a CMDB/file for asset data (optional). | |
| BLUETEAM_IOC_STORE | No | Path to a persistent IOC store (optional). | |
| HUDSONROCK_API_KEY | No | API key for HudsonRock stealer log checks. Optional. | |
| MCP_API_KEY_SCOPES | No | Spaced-separated scopes for the API key. Default 'wazuh:read'. Add 'wazuh:write' for write tools. | wazuh:read |
| VIRUSTOTAL_API_KEY | No | API key for VirusTotal threat intelligence. Optional. | |
| WAZUH_API_PASSWORD | No | The password for the Wazuh Manager API. Required if WAZUH_API_URL is set. | |
| WAZUH_INDEXER_USER | Yes | The username for the Wazuh Indexer. | |
| BLUETEAM_CASE_STORE | No | Path to a case store (optional). | |
| BLUETEAM_RATE_LIMIT | No | Optional per-minute global cap for destructive tools (e.g., fail2ban unban, tcpdump). | |
| WAZUH_API_VERIFY_SSL | No | Whether to verify TLS certificates for the Wazuh Manager API. Default true. | true |
| WAZUH_DISABLED_TOOLS | No | Comma-separated list of individual tools to disable (optional). | |
| BLUETEAM_OWNED_DOMAINS | No | Comma-separated list of your organization's domains (e.g., 'tangerangkota.go.id') used by the redaction policy. | |
| WAZUH_INDEXER_PASSWORD | Yes | The password for the Wazuh Indexer. | |
| BLUETEAM_FORENSIC_TOKEN | No | Shared token required to use raw redaction or full forensics unmasking. The LLM must receive this token explicitly. | |
| BLUETEAM_ALLOWED_ORIGINS | No | Comma-separated allowed origins for browser-based requests. Loopback is always allowed. | |
| BLUETEAM_HTTP_RATE_LIMIT | No | Per-client-IP sliding-window rate limit for inbound HTTP (requests/min, 0=disabled). Default 0. | 0 |
| WAZUH_INDEXER_VERIFY_SSL | No | Whether to verify TLS certificates for the Wazuh Indexer. Default true. | true |
| BLUETEAM_ATTAKER_REGISTRY | No | Path to a persistent attacker registry (optional). | |
| BLUETEAM_REDACTION_POLICY | No | Redaction policy: 'full', 'protect_victim', or 'raw'. Default 'protect_victim'. | protect_victim |
| WAZUH_DISABLED_CATEGORIES | No | Comma-separated list of tool categories to disable (optional). | |
| BLUETEAM_FALSE_POSITIVE_KB | No | Path to a false-positive knowledge base (optional). | |
| BLUETEAM_ALLOW_RUNIME_DOMAINS | No | If 'true', allows runtime update of owned domains via blueteam_set_owned_domains. Default off. | false |
| BLUETEAM_ALLOW_FORENSIC_BYPASS | No | Set to 'true' to enable raw redaction/forensic bypass. Default false. | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/INFOKOM-KI/Wazuh-MCP-Server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server