How do I configure the Prometheus server URL?
Set the `PROMETHEUS_BASE_URL` environment variable to the desired Prometheus HTTP endpoint. The default is `http://localhost:9090`.
@weetime
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"prometheus-mcp-server-weetime": {
"command": "npx",
"args": [
"prometheus-mcp-server"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
A TypeScript-based Model Context Protocol (MCP) server that bridges Claude and Prometheus, enabling querying of metrics, series, labels, alerts, rules, and server status via PromQL.
Install globally with npm install -g prometheus-mcp-server or run via npx prometheus-mcp-server. Configure the Prometheus URL using the PROMETHEUS_BASE_URL environment variable (defaults to http://localhost:9090). Add the server to Claude Desktop’s config file (MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%/Claude/claude_desktop_config.json) with the appropriate command and env settings.
Set the `PROMETHEUS_BASE_URL` environment variable to the desired Prometheus HTTP endpoint. The default is `http://localhost:9090`.
It provides nine MCP functions: `mcp__instant_query`, `mcp__range_query`, `mcp__get_series`, `mcp__get_label_values`, `mcp__get_metadata`, `mcp__get_targets`, `mcp__get_alerts`, `mcp__get_rules`, and `mcp__get_status`.
Use npx: `npx prometheus-mcp-server`. You can also set the `PROMETHEUS_BASE_URL` environment variable inline when using npx.
It communicates over stdio, as is standard for MCP servers (mentioning stdio in the Debugging section for inspecting and debugging).
The server is a TypeScript project that compiles to JavaScript; Node.js is required to run it. All dependencies are bundled via npm.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Multi-zone MCP server for GKE/EKS/AKS: Python tools from git, NeMo guardrails, SSO, autoscaling.
Comments