A
licenseA
qualityA
maintenanceReal-time cluster health monitoring, pre-request NLMS latency prediction, and intelligent prompt routing across multi-instance LLM backends (vLLM, Ollama, SGLang, TGI).
4
4
3
Apache 2.0
Best Prometheus MCP Servers
Prometheus is an open-source systems monitoring and alerting toolkit. It collects and stores metrics as time series data, with flexible queries and real-time alerting.
Why this server?
Scrapes backend engine Prometheus /metrics to inform routing decisions, such as KV-cache utilization and queue depth.
Why this server?
Enables metrics management and querying through support for Prometheus remote_write/read and PromQL.
AlicenseAqualityAmaintenanceArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB and Redis. ArcadeDB is a conceptual fork of OrientDB, the first Multi-Model DBMS. ArcadeDB supports Vector Embeddings.101,193Apache 2.0Why this server?
Allows querying Prometheus metrics via prometheusQuery* table functions.
Why this server?
Provides a tool to retrieve BlazingCDN metrics in Prometheus format, enabling monitoring and alerting with Prometheus.
BlazingCDN-MCPofficial
AlicenseAqualityBmaintenanceOfficial MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Cloud Storage and Video CDN2964 npm2MITWhy this server?
Fronts the Prometheus MCP server (shipped as a mock in the repo and available as a real server), routing requests to PromQL queries, metric names/metadata, and scrape target tools.
jev-routerofficial
AlicenseAqualityCmaintenanceEnables agents to connect through a single gateway that has a decision model pick which MCP tools and playbooks are relevant to each request, so the LLM only sees the few schemas it needs, and to then invoke those tools on the underlying servers. This cuts tool-selection cost and prompt size dramatically when many MCP servers are connected.2MITWhy this server?
Reads and remote-writes per-pattern volume and cost series to a Prometheus backend using PROMETHEUS_REMOTE_WRITE_URL / PROMETHEUS_URL, enabling per-pattern metric backfill and queries.
Log10x MCP Serverofficial
AlicenseAqualityBmaintenanceEnables AI assistants to query per-pattern log cost attribution, investigate cost spikes and incidents, and surface savings opportunities in plain English. It exposes the 10x platform's tools for log analysis, savings estimation, pattern mitigation, and event retrieval, with read-only demo mode available without an API key.554,466 npm1MITWhy this server?
Integrates with Prometheus for monitoring fleet conservation balance, convergence metrics, and agent status metrics.
AlicenseAqualityDmaintenanceEnables Claude Code to query and control the SuperInstance fleet, including fleet status, conservation law checks, semantic search, and agent registry.810 npmMITWhy this server?
Allows monitoring Prometheus endpoints and metrics as a check type, and exposes /metrics.
AlicenseAqualityAmaintenanceUptime monitoring from your AI agent: create and diagnose checks (40 types: HTTP, TCP, DNS, SSL, ICMP, databases, message queues and more), read results and incidents, and manage status pages and maintenance windows. Built into the self-hostable SolidPing server, served over streamable HTTP at /api/v1/mcp.4212AGPL 3.0Why this server?
Allows querying Prometheus metrics.
AlicenseBqualityCmaintenanceA comprehensive MCP server for infrastructure operations with 92 tools across 13 categories, covering system monitoring, networking, containers, multi-cloud management, databases, CI/CD, IaC, security, and remote SSH fleet management.921MIT
