ossec-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ossec-mcp show recent critical alerts"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
OSSEC MCP Server
A fully functional Model Context Protocol (MCP) server for OSSEC HIDS (Host-based Intrusion Detection System). This server exposes OSSEC's security monitoring capabilities as MCP tools, resources, and prompts -- enabling AI assistants to query alerts, manage agents, inspect rules, run integrity checks, and more.
Features
Tools (26 tools)
Category | Tool | Description |
Alerts |
| Retrieve alerts with filtering by level, group, time range, and search |
| Aggregated alert statistics by severity, group, and top rules | |
| Free-text search across all alert data | |
Agents |
| List all managed agents with status |
| Detailed info for a specific agent | |
| Register a new agent | |
| Remove an agent registration | |
| Restart an agent remotely | |
Rules |
| Search rules by ID, level, group, or keyword |
| Full rule definition with match criteria | |
| List all rule XML files | |
| Search and list log decoders | |
Syscheck |
| File Integrity Monitoring results |
| Trigger a FIM scan | |
| Reset FIM baseline | |
Rootcheck |
| Rootkit/anomaly detection results |
| Trigger rootcheck scan | |
Status |
| Service health for all daemons |
| Restart all OSSEC services | |
| Internal OSSEC logs with filtering | |
| Processing statistics | |
| Parsed configuration (full or by section) | |
| Raw ossec.conf XML | |
Log Test |
| Test log lines against rules/decoders |
Response |
| List configured active responses |
| Execute active response on an agent |
Resources (8 static resources + 3 resource templates)
Static resources:
URI | Description |
| Current service status |
| Last 50 alerts |
| Critical alerts (level 12+, last 24h) |
| All agents |
| Parsed configuration |
| Raw XML configuration |
| Rule files summary |
| Recent internal logs |
Resource templates (dynamic, parameterized):
URI Template | Description |
| Specific agent detail |
| Agent FIM results |
| Agent rootcheck results |
Prompts (5 prompts)
Prompt | Description |
| Structured security alert analysis with recommendations |
| Deep-dive investigation of a specific agent |
| Comprehensive OSSEC deployment audit |
| Guided IR workflow for security events |
| Rule tuning to reduce false positives |
Related MCP server: wazuh-mcp-server
Security
This server includes several hardening measures:
Secure XML parsing -- Uses
defusedxmlto prevent XXE and billion laughs attacks when parsing OSSEC rules, decoders, and configuration files.Input validation -- All user-supplied parameters (
agent_id, agentname,ip,command,filename) are validated against strict regex patterns before being passed to CLI tools or the API, preventing command injection and path traversal.Path traversal prevention -- Filename parameters used in filesystem
glob()calls reject path separators and..sequences.Error sanitization -- Error messages returned to clients have filesystem paths stripped to avoid leaking internal directory structure.
Bounded resource usage -- File reads are capped at 10 MB, log tail operations use bounded memory, and query limits are clamped to configured maximums.
Secure defaults -- SSE transport binds to
127.0.0.1by default (not0.0.0.0). API communication always uses HTTPS.No shell execution -- All subprocess calls use
create_subprocess_execwith argument lists, never shell strings.
Installation
Prerequisites
Python 3.10+
OSSEC HIDS installed (local mode) or Wazuh/OSSEC API access (API mode)
Linux host (or Windows with WSL) for local mode
Installing OSSEC HIDS
If OSSEC is not already installed, you can compile it from source. Example for Debian/Ubuntu/Kali:
# Install build dependencies
sudo apt update && sudo apt install -y \
build-essential make gcc libssl-dev libpcre2-dev \
zlib1g-dev wget libsystemd-dev
# Download OSSEC 3.7.0
cd /tmp
wget https://github.com/ossec/ossec-hids/archive/refs/tags/3.7.0.tar.gz
tar -zxf 3.7.0.tar.gz
cd ossec-hids-3.7.0
# Create non-interactive install config
cat > etc/preloaded-vars.conf << 'EOF'
USER_LANGUAGE="en"
USER_NO_STOP="y"
USER_INSTALL_TYPE="local"
USER_DIR="/var/ossec"
USER_DELETE_DIR="y"
USER_ENABLE_ACTIVE_RESPONSE="y"
USER_ENABLE_SYSCHECK="y"
USER_ENABLE_ROOTCHECK="y"
USER_ENABLE_EMAIL="n"
USER_ENABLE_SYSLOG="y"
USER_ENABLE_FIREWALL_RESPONSE="n"
USER_WHITE_LIST="127.0.0.1"
EOF
# Compile and install
sudo ./install.sh
# Start OSSEC
sudo /var/ossec/bin/ossec-control start
# Verify
sudo /var/ossec/bin/ossec-control statusAfter installation, the following daemons should be running: ossec-analysisd, ossec-logcollector, ossec-syscheckd, ossec-monitord, ossec-execd.
Dependencies
Package | Purpose |
| MCP SDK with FastMCP server framework |
| Data validation |
| Environment/file-based configuration |
| Async HTTP client for API mode |
| Timestamp parsing |
| Secure XML parsing |
Dev dependencies: pytest, pytest-asyncio, ruff
Install from source
# Clone or download the project
cd OSSEC_MCP_SERVER
# Create a virtual environment (recommended)
python3 -m venv .venv
source .venv/bin/activate # Linux/macOS
# .venv\Scripts\activate # Windows
# Install the package
pip install -e .
# Or install with dev dependencies
pip install -e '.[dev]'Configure
# Copy the example environment file
cp .env.example .env
# Edit with your OSSEC settings
# At minimum, verify OSSEC_PATH points to your installationConfiguration is loaded from environment variables or a .env file. All options and their defaults:
Variable | Default | Description |
|
| OSSEC installation root directory |
|
|
|
|
| API hostname (API mode only) |
|
| API port (API mode only) |
|
| API username (API mode only) |
| (empty) | API password (API mode only) |
|
| Verify TLS certificates for API connections |
|
| MCP transport: |
|
| SSE bind address (SSE transport only) |
|
| SSE port (SSE transport only) |
|
| Maximum alerts returned per query |
|
| Default minimum alert level filter |
|
| Logging level ( |
Usage
Run the server
# stdio transport (default -- for AI tool integration)
ossec-mcp-server
# Or run as a Python module
python -m ossec_mcpIf the venv is not activated, use the full path:
/path/to/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-serverSudo / permissions
OSSEC files under /var/ossec/ are owned by root and the ossec user. The MCP server must run with elevated privileges to read alerts, logs, rules, and configuration. Without sudo, most tools will return Permission denied.
There are two ways to handle this:
Option A -- Inline password (simple, stores password in config):
Use sudo -S to feed the password via stdin, then exec sudo to run the server with cached credentials:
echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /path/to/ossec-mcp-serverThe first command authenticates and caches the credential. The exec sudo then runs the server using the cached session -- keeping stdin free for the MCP stdio protocol.
Option B -- Passwordless sudo (more secure, one-time setup):
Add a sudoers rule that allows running only this one binary without a password:
echo 'YOUR_USER ALL=(ALL) NOPASSWD: /path/to/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server' \
| sudo tee /etc/sudoers.d/ossec-mcp
sudo chmod 440 /etc/sudoers.d/ossec-mcpThen the config only needs sudo without any password handling:
sudo /path/to/ossec-mcp-serverAll examples below use Option A (inline password). Replace <PASSWORD> with your Linux sudo password. If you prefer Option B, remove the echo ... | sudo -S true 2>/dev/null; prefix and use sudo directly.
Integration with AI tools
OSSEC is a Linux HIDS. The MCP server needs access to the OSSEC installation -- either locally on the same Linux host, or remotely via the Wazuh/OSSEC REST API.
If your editor is running on the same Linux machine as OSSEC, the commands below work directly. If your editor is on Windows/macOS and OSSEC is in WSL or a remote server, see the "Windows with WSL" and "Remote / API mode" sections further down.
VS Code (GitHub Copilot)
A ready-to-use config file is included at .vscode/mcp.json. After installing the package into the venv, VS Code will pick it up automatically when you open the project folder.
To configure it manually or in another project, create .vscode/mcp.json:
Native Linux:
{
"servers": {
"ossec": {
"type": "stdio",
"command": "bash",
"args": [
"-c",
"echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /path/to/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server"
],
"env": {
"OSSEC_PATH": "/var/ossec",
"OSSEC_MODE": "local"
}
}
}
}Windows with WSL:
{
"servers": {
"ossec": {
"type": "stdio",
"command": "wsl.exe",
"args": [
"-d", "kali-linux",
"-e", "bash", "-c",
"echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /mnt/d/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server"
],
"env": {
"OSSEC_PATH": "/var/ossec",
"OSSEC_MODE": "local"
}
}
}
}Then in VS Code: open Copilot Chat, switch to Agent mode, and the OSSEC tools will be available.
Claude Code (CLI)
A ready-to-use config file is included at .mcp.json in the project root. Claude Code reads this automatically when you run claude from this directory.
To add it manually:
claude mcp add ossec \
-e OSSEC_PATH=/var/ossec \
-e OSSEC_MODE=local \
-- bash -c "echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /path/to/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server"Or create/edit .mcp.json in the project root:
{
"mcpServers": {
"ossec": {
"command": "bash",
"args": [
"-c",
"echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /path/to/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server"
],
"env": {
"OSSEC_PATH": "/var/ossec",
"OSSEC_MODE": "local"
}
}
}
}For global availability across all projects, add to ~/.claude.json instead.
Claude Desktop
Edit the config file at:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
Native Linux / macOS:
{
"mcpServers": {
"ossec": {
"command": "bash",
"args": [
"-c",
"echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /path/to/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server"
],
"env": {
"OSSEC_PATH": "/var/ossec",
"OSSEC_MODE": "local"
}
}
}
}Windows with WSL:
{
"mcpServers": {
"ossec": {
"command": "wsl.exe",
"args": [
"-d", "kali-linux",
"-e", "bash", "-c",
"echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /mnt/d/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server"
],
"env": {
"OSSEC_PATH": "/var/ossec",
"OSSEC_MODE": "local"
}
}
}
}Cursor
A ready-to-use config file is included at .cursor/mcp.json. Cursor reads this automatically when you open the project.
To configure manually, create .cursor/mcp.json in the project root:
Native Linux:
{
"mcpServers": {
"ossec": {
"command": "bash",
"args": [
"-c",
"echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /path/to/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server"
],
"env": {
"OSSEC_PATH": "/var/ossec",
"OSSEC_MODE": "local"
}
}
}
}Windows with WSL:
{
"mcpServers": {
"ossec": {
"command": "wsl.exe",
"args": [
"-d", "kali-linux",
"-e", "bash", "-c",
"echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /mnt/d/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server"
],
"env": {
"OSSEC_PATH": "/var/ossec",
"OSSEC_MODE": "local"
}
}
}
}Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
Native Linux:
{
"mcpServers": {
"ossec": {
"command": "bash",
"args": [
"-c",
"echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /path/to/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server"
],
"env": {
"OSSEC_PATH": "/var/ossec",
"OSSEC_MODE": "local"
}
}
}
}Windows with WSL:
{
"mcpServers": {
"ossec": {
"command": "wsl.exe",
"args": [
"-d", "kali-linux",
"-e", "bash", "-c",
"echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /mnt/d/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server"
],
"env": {
"OSSEC_PATH": "/var/ossec",
"OSSEC_MODE": "local"
}
}
}
}Windows with WSL (summary)
All the per-tool sections above already include Windows with WSL examples. The key pattern is:
wsl.exe -d <DISTRO> -e bash -c "echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo <ABSOLUTE_PATH_TO_SERVER>"Replace:
<DISTRO>with your WSL distro name (runwsl -lto list, e.g.,kali-linux)<PASSWORD>with your Linux sudo password<ABSOLUTE_PATH_TO_SERVER>with the full path, e.g.,/mnt/d/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server
Claude Code (on Windows):
claude mcp add ossec \
-e OSSEC_PATH=/var/ossec \
-e OSSEC_MODE=local \
-- wsl.exe -d kali-linux -e bash -c \
"echo '<PASSWORD>' | sudo -S true 2>/dev/null; exec sudo /mnt/d/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server"Remote / API mode
If OSSEC runs on a remote server and you cannot run the MCP server locally alongside it, use API mode. The MCP server connects to the Wazuh/OSSEC REST API over HTTPS:
{
"mcpServers": {
"ossec": {
"command": "/path/to/OSSEC_MCP_SERVER/.venv/bin/ossec-mcp-server",
"env": {
"OSSEC_MODE": "api",
"OSSEC_API_HOST": "192.168.1.100",
"OSSEC_API_PORT": "55000",
"OSSEC_API_USER": "admin",
"OSSEC_API_PASSWORD": "your-password",
"OSSEC_API_SSL_VERIFY": "false"
}
}
}
}This works from any machine -- Windows, macOS, or Linux -- as long as it can reach the API endpoint over the network.
SSE transport
For network-accessible deployment (e.g., shared MCP server for multiple clients):
MCP_TRANSPORT=sse MCP_HOST=0.0.0.0 MCP_PORT=8000 ossec-mcp-serverSSE binds to 127.0.0.1 by default. Set MCP_HOST=0.0.0.0 explicitly to expose it externally.
Connection Modes
Local mode (default)
Interacts directly with OSSEC on the same host via:
CLI tools:
ossec-control,manage_agents,agent_control,syscheck_control,rootcheck_control,ossec-logtestFilesystem: Reads alerts (JSON and plain-text formats), internal logs, rule XML files, decoder XML files, and
ossec.confdirectly
Requires the server to run on the same machine as the OSSEC manager, or to have filesystem access to the OSSEC installation directory (e.g., via WSL mounts).
API mode
Connects to the OSSEC/Wazuh REST API over HTTPS. Use this when the MCP server runs on a different machine than the OSSEC manager. Set OSSEC_MODE=api and configure the API connection variables. See the "Remote / API mode" example in the Usage section above.
OSSEC Alert Levels Reference
Level | Severity | Description |
0 | Ignored | Not classified |
1--3 | Low | System notifications, successful events |
4--6 | Medium | Errors, warnings, bad configurations |
7--9 | High | Bad words detected, first-time events |
10--11 | Very High | Multiple failures, integrity changes |
12--14 | Critical | Firewall drops, high-impact events |
15--16 | Severe | Attack success, critical integrity changes |
Testing
The project includes four test suites (356 tests total):
# Activate the virtual environment
source .venv/bin/activate
# Unit and integration tests (167 tests)
python tests/test_comprehensive.py
# Security validation tests (72 tests)
python tests/test_security.py
# Live MCP protocol tests via official SDK client (105 tests)
python tests/test_mcp_sdk_protocol.py
# Live OSSEC integration tests (12 tests) -- requires a running OSSEC installation
sudo .venv/bin/python tests/test_live_ossec.pyThe security tests validate input sanitization, path traversal prevention, XML safety (defusedxml), error message sanitization, timezone-aware datetime handling, boundary clamping, and exact group matching.
The MCP protocol tests spawn the server as a subprocess and connect a real MCP SDK client to verify initialization, tool listing, tool calls, resource reads, and prompt retrieval over the stdio transport.
The live OSSEC integration tests run the OssecClient directly against a real OSSEC installation, exercising service status, log retrieval, rule/decoder parsing, alert queries, syscheck, rootcheck, agent listing, stats, and configuration reads. These require sudo since OSSEC files are owned by the ossec user.
Project Structure
OSSEC_MCP_SERVER/
├── pyproject.toml # Build config, dependencies, entry point
├── .env.example # Configuration template
├── .mcp.json # Claude Code MCP config (auto-detected)
├── .vscode/mcp.json # VS Code MCP config (auto-detected)
├── .cursor/mcp.json # Cursor MCP config (auto-detected)
├── README.md
├── .gitignore
├── src/
│ └── ossec_mcp/
│ ├── __init__.py # Package version (1.0.0)
│ ├── __main__.py # python -m ossec_mcp support
│ ├── server.py # FastMCP server creation and entry point
│ ├── config.py # Settings via pydantic-settings
│ ├── ossec_client.py # OSSEC interaction layer (CLI + API)
│ ├── tools/
│ │ ├── alerts.py # get_alerts, get_alert_summary, search_alerts
│ │ ├── agents.py # list_agents, get_agent_info, add/remove/restart_agent
│ │ ├── rules.py # get_rules, get_rule_details, list_rule_files, get_decoders
│ │ ├── syscheck.py # get_syscheck_results, run_syscheck_scan, clear_syscheck_database
│ │ ├── rootcheck.py # get_rootcheck_results, run_rootcheck_scan
│ │ ├── status.py # get_ossec_status, restart_ossec, logs, stats, config
│ │ ├── logtest.py # run_logtest
│ │ └── active_response.py # get_active_responses, run_active_response
│ ├── resources/
│ │ └── providers.py # 8 static resources + 3 resource templates
│ └── prompts/
│ └── templates.py # 5 prompt templates
└── tests/
├── test_comprehensive.py # 167 unit/integration tests
├── test_security.py # 72 security validation tests
├── test_mcp_sdk_protocol.py # 105 live MCP protocol tests
└── test_live_ossec.py # 12 live OSSEC integration testsLicense
Available Tools
26 toolsadd_agentA
Add a new agent to the OSSEC manager.
Registers a new agent with the specified name and IP address. The agent will need to be authenticated and configured to connect.
Args: name: Unique name for the new agent (e.g., 'webserver-01'). ip: IP address of the agent (e.g., '10.0.0.10'). Use 'any' for dynamic IPs.
Returns: JSON object with the result including the new agent's ID and key.
Inputs: name (required), ip (required). Returns: result
clear_syscheck_databaseA
Clear the syscheck database for an agent.
Removes all stored file integrity data. The next scan will create a new baseline.
Args: agent_id: Agent ID whose database to clear (default: '000' for the manager).
Returns: JSON object indicating success or failure.
Inputs: agent_id. Returns: result
get_active_responsesA
Get configured active response rules.
Active responses are automated actions OSSEC can take when specific alerts trigger, such as blocking an IP, restarting a service, or running a custom script.
Returns: JSON array of active response configurations including command, location, rules_id, and timeout.
Inputs: no named parameters. Returns: result
get_agent_infoA
Get detailed information about a specific OSSEC agent.
Retrieves comprehensive details including agent name, IP, OS info, last keep-alive time, group membership, and current status.
Args: agent_id: The agent ID (e.g., '001', '002'). Use '000' for the manager.
Returns: JSON object with detailed agent information.
Inputs: agent_id (required). Returns: result
get_alertsA
Retrieve recent OSSEC security alerts with optional filtering.
Args: limit: Maximum number of alerts to return (default: 50, max: 500). level_min: Minimum alert severity level (0-16). Level 0 = ignored, 3 = successful events, 5 = user errors, 7 = bad words, 10 = multiple failures, 12 = high importance, 15 = severe. level_max: Maximum alert severity level (0-16). group: Filter by rule group (e.g., 'syslog', 'sshd', 'authentication_failed'). search: Free-text search across alert content. time_range: Time range filter. Examples: '1h' (last hour), '24h' (last day), '7d' (last week), '30m' (last 30 minutes).
Returns: JSON array of alert objects containing timestamp, rule info, agent details, etc.
Inputs: limit, level_min, level_max, group, +2 more. Returns: result
get_alert_summaryA
Get a summary of OSSEC alerts over a time period.
Provides counts grouped by severity level, rule group, and top triggered rules.
Args: time_range: Time range to summarize. Examples: '1h', '24h', '7d'. Default: '24h'.
Returns: JSON summary with alert counts by level, group, and top rules.
Inputs: time_range. Returns: result
get_decodersA
Search and retrieve OSSEC log decoders.
Decoders are used to parse and normalize log data before it is evaluated against rules. They extract fields like source IP, username, program name, etc.
Args: search: Free-text search in decoder names. filename: Filter by decoder file name (e.g., 'local_decoder.xml').
Returns: JSON array of decoder objects with name, parent, fields extracted, etc.
Inputs: search, filename. Returns: result
get_ossec_configurationA
Read the OSSEC configuration (ossec.conf).
Retrieves the parsed configuration. Can return the full config or a specific section.
Args: section: Optional configuration section to retrieve. Common sections: 'global', 'alerts', 'syscheck', 'rootcheck', 'localfile', 'remote', 'rules', 'command', 'active-response', 'syslog_output'. If not specified, returns the full configuration.
Returns: JSON object with the parsed configuration.
Inputs: section. Returns: result
get_ossec_configuration_rawA
Get the raw OSSEC configuration file content.
Returns the complete ossec.conf file as plain text, preserving all XML formatting and comments.
Returns: The raw content of ossec.conf.
Inputs: no named parameters. Returns: result
get_ossec_logsA
Get OSSEC internal logs (ossec.log).
Retrieves the latest entries from OSSEC's own log file, useful for troubleshooting and monitoring OSSEC's operation.
Args: lines: Number of log lines to retrieve (default: 100). category: Optional filter by log category (e.g., 'ossec-analysisd', 'ossec-remoted', 'error', 'warning').
Returns: JSON array of log lines.
Inputs: lines, category. Returns: result
get_ossec_statsA
Get OSSEC processing statistics.
Retrieves statistics about events analyzed, alerts generated, firewall events, and other metrics.
Args: date: Optional date filter (YYYY-MM-DD format). Default: current day.
Returns: JSON object with statistical data.
Inputs: date. Returns: result
get_ossec_statusA
Get the current status of all OSSEC services.
Checks whether each OSSEC daemon is running or stopped, including: ossec-analysisd, ossec-remoted, ossec-syscheckd, ossec-logcollector, ossec-maild, ossec-execd, and ossec-monitord.
Returns: JSON object with service status, running count, and overall state.
Inputs: no named parameters. Returns: result
get_rootcheck_resultsA
Get rootcheck results for an agent.
Rootcheck performs system auditing, checking for rootkits, trojans, hidden processes, suspicious files, and system anomalies.
Args: agent_id: Agent ID to query (default: '000' for the manager).
Returns: JSON object with rootcheck findings.
Inputs: agent_id. Returns: result
get_rule_detailsA
Get the full details of a specific OSSEC rule by its ID.
Returns the complete rule definition including all matching criteria, parent rules, frequency settings, and associated group.
Args: rule_id: The rule ID to look up (e.g., '5710').
Returns: JSON object with the complete rule definition.
Inputs: rule_id (required). Returns: result
get_rulesA
Search and retrieve OSSEC detection rules.
OSSEC rules define what events trigger alerts. Each rule has an ID, severity level, group classification, and matching criteria.
Args: rule_id: Filter by specific rule ID (e.g., '5710' for SSH brute force). level_min: Minimum rule level (0-16). level_max: Maximum rule level (0-16). group: Filter by rule group (e.g., 'sshd', 'web', 'syslog', 'authentication_failed'). search: Free-text search in rule descriptions. filename: Filter by rule file name (e.g., 'sshd_rules.xml').
Returns: JSON array of rule objects with id, level, description, groups, and match criteria.
Inputs: rule_id, level_min, level_max, group, +2 more. Returns: result
get_syscheck_resultsA
Get File Integrity Monitoring (FIM) results for an agent.
Syscheck monitors files and directories for changes. It detects modifications to file content, permissions, ownership, and attributes.
Args: agent_id: Agent ID to query (default: '000' for the manager). file: Optional specific file path to check (e.g., '/etc/passwd').
Returns: JSON object with syscheck results including changed files and their details.
Inputs: agent_id, file. Returns: result
list_agentsA
List all OSSEC agents managed by this server.
Retrieves the full list of agents including their ID, name, IP address, and status information.
Args: status: Optional filter by agent status. Valid values: 'active', 'disconnected', 'never_connected', 'pending'. If not specified, returns all agents.
Returns: JSON array of agent objects with id, name, ip, and status.
Inputs: status. Returns: result
list_rule_filesA
List all OSSEC rule files.
Returns the file names of all rule XML files, which can be used to inspect or filter rules by file.
Returns: JSON array of rule file information including filename and path.
Inputs: no named parameters. Returns: result
remove_agentA
Remove an agent from the OSSEC manager.
Permanently removes the agent registration. The agent will no longer be able to connect to the manager.
Args: agent_id: The agent ID to remove (e.g., '001').
Returns: JSON object indicating success or failure.
Inputs: agent_id (required). Returns: result
restart_agentA
Restart a specific OSSEC agent.
Sends a restart command to the agent, causing it to reload its configuration and reconnect.
Args: agent_id: The agent ID to restart (e.g., '001').
Returns: JSON object indicating success or failure.
Inputs: agent_id (required). Returns: result
restart_ossecA
Restart all OSSEC services.
Stops and restarts all OSSEC daemons. Use this after making configuration changes to apply them.
Returns: JSON object indicating success or failure with service output.
Inputs: no named parameters. Returns: result
run_active_responseA
Execute an active response command on an agent.
Triggers a configured active response action on a specific agent. Common commands include firewall-drop, host-deny, disable-account, etc.
⚠️ WARNING: This performs real actions on the agent! Ensure you understand the command's effect before executing.
Args: agent_id: Target agent ID (e.g., '001'). Use '000' for the manager. command: Active response command name (e.g., 'firewall-drop', 'host-deny', 'restart-ossec', 'disable-account'). arguments: Optional space-separated arguments (e.g., IP to block: '10.0.0.5').
Returns: JSON object indicating success or failure.
Inputs: agent_id (required), command (required), arguments. Returns: result
run_logtestA
Test a log line against OSSEC rules and decoders.
Runs a log line through OSSEC's analysis engine to see how it would be decoded, which rules it matches, and what alert level it would generate. Extremely useful for debugging rules and decoders.
Args: log_line: The log line to test (e.g., a syslog line, auth.log entry, etc.). verbose: If True, include verbose rule matching details.
Returns: JSON object with decoding results, matched rules, and alert info.
Example log lines to test: - 'Mar 12 10:00:00 server sshd[1234]: Failed password for root from 10.0.0.1 port 22' - 'Mar 12 10:00:00 server sudo: user1 : TTY=pts/0 ; PWD=/home ; COMMAND=/bin/su -'
Inputs: log_line (required), verbose. Returns: result
run_rootcheck_scanA
Trigger a rootcheck scan on an agent.
Initiates a new rootcheck scan that will check for rootkits, trojans, and other security issues.
Args: agent_id: Agent ID to scan (default: '000' for the manager).
Returns: JSON object indicating whether the scan was triggered successfully.
Inputs: agent_id. Returns: result
run_syscheck_scanA
Trigger a File Integrity Monitoring scan on an agent.
Initiates a new syscheck scan that will check all monitored files and directories for changes since the last scan.
Args: agent_id: Agent ID to scan (default: '000' for the manager).
Returns: JSON object indicating whether the scan was triggered successfully.
Inputs: agent_id. Returns: result
search_alertsA
Search OSSEC alerts using a free-text query.
Searches across all alert fields including rule descriptions, source IPs, agent names, log content, and more.
Args: query: Search string to match across alert content. limit: Maximum number of matching alerts to return (default: 50). time_range: Optional time range filter (e.g., '1h', '24h', '7d').
Returns: JSON array of matching alert objects.
Inputs: query (required), limit, time_range. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 26 tools
Each tool targets a distinct OSSEC functionality or resource. Even closely related tools like get_alerts, search_alerts, and get_alert_summary have clearly separate purposes (recent retrieval, free-text search, summary aggregation). There is no meaningful overlap between any tools.
All tools follow a consistent verb_noun pattern in snake_case (e.g., add_agent, get_alerts, run_syscheck_scan). The verbs are descriptive and the nouns are the OSSEC resources. No mixed conventions or irregular names.
With 26 tools, the server covers the full OSSEC management surface—agents, alerts, rules, syscheck, rootcheck, configuration, active responses, logs, stats, and status. Each tool serves a necessary purpose without redundancy, making the set well-scoped for a security monitoring MCP.
The tool set provides comprehensive CRUD-like operations for most OSSEC domains, including agent lifecycle, alert analysis, rule management, and scans. Minor gaps exist (e.g., no agent key revocation, no agent rekeying), but these are not critical for typical management workflows.
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceAn MCP server that exposes a 60+ tool security and threat-intel stack to AI agents, enabling secret scanning, Sigma rule generation, ransomware lookup, OSINT, and deep research.1MIT
- AlicenseAqualityBmaintenanceAI-powered MCP server that enables security analysts to query Wazuh SIEM/XDR for alert triage, threat hunting, compliance audits, and incident response through natural language prompts.2813MIT
- AlicenseNot gradedqualityDmaintenanceA comprehensive MCP server that exposes multiple OSINT tools to AI assistants like Claude, enabling sophisticated reconnaissance and information gathering tasks using industry-standard OSINT tools.249MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables conversational interaction with Wazuh SIEM, allowing users to investigate alerts, hunt threats, tune false positives, edit rules, and run security actions via natural language.MIT