Install
$ agentstack add mcp-ggilligan12-kibana-mcp ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Kibana MCP Server
Model Context Protocol (MCP) server for Kibana Security - manage alerts, rules, and exceptions via AI assistants.
Quick Start
1. Clone and Build
git clone https://github.com/ggilligan12/kibana-mcp.git
cd kibana-mcp
docker build -t kibana-mcp .
2. Configure MCP Client
Add to your MCP client config (Claude Desktop, Cursor, etc.):
Option A: Using Environment Variables (Recommended)
First, set your credentials:
export KIBANA_URL="https://your-kibana.example.com:5601"
# Option 1: API Key (recommended)
export KIBANA_API_KEY="your_base64_api_key"
# Option 2: Username/Password
# export KIBANA_USERNAME="your_username"
# export KIBANA_PASSWORD="your_password"
Then add to your MCP config:
{
"mcpServers": {
"kibana-mcp": {
"command": "docker",
"args": ["run", "-i", "--rm", "--network", "host", "-e", "KIBANA_URL", "-e", "KIBANA_API_KEY", "kibana-mcp"]
}
}
}
For username/password, use:
{
"mcpServers": {
"kibana-mcp": {
"command": "docker",
"args": ["run", "-i", "--rm", "--network", "host", "-e", "KIBANA_URL", "-e", "KIBANA_USERNAME", "-e", "KIBANA_PASSWORD", "kibana-mcp"]
}
}
}
Option B: Direct Credentials (Easier for Claude Desktop)
Using API Key:
{
"mcpServers": {
"kibana-mcp": {
"command": "docker",
"args": [
"run", "-i", "--rm", "--network", "host",
"-e", "KIBANA_URL=https://your-kibana.example.com:5601",
"-e", "KIBANA_API_KEY=your_base64_api_key",
"kibana-mcp"
]
}
}
}
Using Username/Password:
{
"mcpServers": {
"kibana-mcp": {
"command": "docker",
"args": [
"run", "-i", "--rm", "--network", "host",
"-e", "KIBANA_URL=https://your-kibana.example.com:5601",
"-e", "KIBANA_USERNAME=your_username",
"-e", "KIBANA_PASSWORD=your_password",
"kibana-mcp"
]
}
}
}
Note: Option B is less secure but more convenient for tools like Claude Desktop where environment variables are harder to manage.
Available Tools
get_alerts- Fetch security alertstag_alert- Add tags to alertsadjust_alert_status- Change alert status (open/acknowledged/closed)find_rules- Search detection rulesget_rule_exceptions- Get rule exception itemsadd_rule_exception_items- Add exceptions to rulescreate_exception_list- Create new exception listsassociate_shared_exception_list- Link exception lists to rules
Local Development
# Install dependencies
uv sync
# Set environment variables (see above)
# Run locally
uv run kibana-mcp
Test Environment
# Start local Kibana/Elasticsearch with test data
pip install -r testing/requirements-dev.txt
./testing/quickstart-test-env.sh
# Access at http://localhost:5601 (elastic/elastic)
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ggilligan12
- Source: ggilligan12/kibana-mcp
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.