nightingale
Nightingale is to monitoring and alerting what Grafana is to visualization.
The Nightingale MCP server is a built-in endpoint within the Nightingale monitoring platform that enables AI assistants to query and manage alerting rules, dashboards, and observability data through natural language. The server exposes 74 fine-grained tools across 13 toolsets covering alerts, data sources, dashboards, users, metrics, and logs, all authenticated via personal access tokens or OAuth 2.1. It operates over the Streamable HTTP transport at the /mcp path, with RBAC permissions applied based on the authenticated user's access level.
Key Features
Use Cases
- 01Query active alerts and alert history using natural language in Claude Desktop or Cursor
- 02Create and update alerting rules through conversational AI interfaces
- 03Explore monitoring metrics and logs across multiple data sources via AI assistants
- 04Manage dashboards and visualization configurations without using the web UI
- 05Configure notification rules and alert subscriptions through ChatGPT or other MCP clients
- 06Integrate Nightingale alerting management into enterprise AI workflows with OAuth-based authentication
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
nightingale — FAQ
What is the Nightingale MCP server?+
It is a built-in MCP endpoint within the Nightingale monitoring platform that exposes 74 tools for managing alerts, dashboards, metrics, and logs through AI assistants. The server runs as part of the main Nightingale process with no additional deployment required.
How do I connect an MCP client to Nightingale?+
Configure your MCP client to connect to http(s)://<nightingale>:17000/mcp using the http transport type. You must authenticate with a personal access token created in the Nightingale web UI under Profile → Token Management, passed in the X-User-Token header.
Which AI clients work with the Nightingale MCP server?+
Any MCP-compatible client works, including Claude Desktop, Claude Code, Cursor, ChatGPT with MCP connectors, and custom agents that support the Model Context Protocol over HTTP.
Do I need an API key or special prerequisites?+
You need a personal access token from your Nightingale instance, which you create in the web UI. The /mcp endpoint must be enabled in the configuration (it is enabled by default), and HTTP.TokenAuth must be active for authentication.
Is the Nightingale MCP server free and open source?+
Yes, it is open source under the Apache License 2.0 and included in the main Nightingale project at no cost.
Can I enable write operations like creating or deleting alerts?+
The server is read-only by default for safety. To enable write tools (create, update, delete operations), set MCPEnableWriteTools = true in the [HTTP.A2A] section of etc/config.toml.
How do I install nightingale?+
Open the source repository on GitHub and follow its README. nightingale is a mcp server — MCP Agents Market links you directly to the official repo.
Is nightingale free?+
nightingale is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.