Nightingale
Nightingale's official MCP Server
What is Nightingale?
Nightingale is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to nightingale's official mcp server
Nightingale's official MCP Server
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Nightingale's official MCP Server
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx n9eConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Nightingale
The Nightingale (n9e) MCP server is the official integration between the Nightingale open-source monitoring platform and MCP-compatible AI assistants. It exposes tools across 13 toolsets — including alerts, targets, metrics, logs, dashboards, and notification rules — allowing engineers to query Prometheus metrics, search Loki/Elasticsearch logs, manage alert rules, and create mute windows directly through natural language. Both read-only and read-write modes are supported, making it suitable for on-call triage workflows as well as automated alerting operations.
Prerequisites
- Nightingale v8.0.0 or later with HTTP.TokenAuth enabled in config.toml
- A Nightingale API token generated from Personal Settings > Token Management
- The Nightingale server URL (e.g. http://your-n9e-server:17000)
- Node.js and npx installed (for the stdio transport), or Docker for HTTP/SSE mode
- An MCP-compatible client such as Claude Desktop or Cursor
Enable token authentication in Nightingale
Edit your Nightingale config.toml and ensure HTTP.TokenAuth is enabled. This is required for the MCP server to authenticate API calls.
Generate a Nightingale API token
Log into the Nightingale web interface, navigate to Personal Settings > Profile > Token Management, and create a new token with the permissions your use case requires (read-only or full access).
Add to your MCP client configuration (stdio mode)
Add the server to your MCP client config using npx with your token and base URL as environment variables. This is the recommended mode for local clients like Claude Desktop and Cursor.
{
"mcpServers": {
"nightingale": {
"command": "npx",
"args": ["-y", "@n9e/n9e-mcp-server", "stdio"],
"env": {
"N9E_TOKEN": "your-api-token",
"N9E_BASE_URL": "http://your-n9e-server:17000"
}
}
}
}Optionally restrict toolsets to reduce context usage
The server loads all 13 toolsets by default, which can consume significant context window space. Use N9E_TOOLSETS to enable only the toolsets you need.
"N9E_TOOLSETS": "alerts,targets,metrics"Enable read-only mode for safe querying
Set N9E_READ_ONLY to true to disable all write operations (create/update/delete). This is recommended for shared environments or when you only need monitoring insights.
"N9E_READ_ONLY": "true"Restart your MCP client and verify
Restart your client. Ask Claude to list active alerts or monitored targets to confirm the connection is working.
Nightingale Examples
Client configuration
Cursor MCP JSON configuration for the Nightingale server in read-only stdio mode.
{
"mcpServers": {
"nightingale": {
"command": "npx",
"args": ["-y", "@n9e/n9e-mcp-server", "stdio"],
"env": {
"N9E_TOKEN": "your-api-token",
"N9E_BASE_URL": "http://your-n9e-server:17000",
"N9E_READ_ONLY": "true",
"N9E_TOOLSETS": "alerts,targets,metrics,logs"
}
}
}
}Prompts to try
Example monitoring and operations questions to ask Claude with the Nightingale server connected.
- "Show all critical alerts fired in the last 24 hours"
- "List monitored targets that have been unreachable for more than 5 minutes"
- "What alert rules are configured for business group 1?"
- "Create a mute window for all alerts tagged service=api for the next 2 hours — scheduled maintenance"
- "Query the CPU usage metric for host web-01 over the last hour and summarize the trend"Troubleshooting Nightingale
Authentication errors — 401 or 403 responses from the Nightingale API
Confirm that HTTP.TokenAuth is set to true in Nightingale's config.toml and that the server has been restarted after the change. Also verify the N9E_TOKEN value matches a valid, non-expired token in Nightingale's Token Management page.
Too many tools overloading the context window
Set N9E_TOOLSETS in the env config to a comma-separated list of only the toolsets you need (e.g. 'alerts,targets,metrics'). Available toolsets: alerts, targets, datasource, mutes, busi_groups, notify_rules, alert_subscribes, event_pipelines, users, metrics, logs, dashboards, roles.
npx command not found or server fails to start
Ensure Node.js 18+ is installed and npx is available in your PATH. Alternatively, use the Docker deployment mode: clone the repo, configure docker-compose.yml with N9E_BASE_URL and N9E_TOKEN, and run 'docker compose up -d --build'.
Frequently Asked Questions about Nightingale
What is Nightingale?
Nightingale is a Model Context Protocol (MCP) server that nightingale's official mcp server It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Nightingale?
Follow the installation instructions on the Nightingale GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Nightingale?
Nightingale works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Nightingale free to use?
Yes, Nightingale is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Nightingale Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to Nightingale? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Nightingale in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Nightingale?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.