MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
kubectl-metricsgithub.com/yaacov/kubectl-metricsupdated this year
Query Prometheus / Thanos metrics on OpenShift clusters — as a CLI and an MCP server for AI assistants.
Apache-2.0 -
@elad-nofy/prometheus-mcpgithub.com/elad-nofy/prometheus-mcpupdated this year
MCP server for Prometheus - Query metrics, targets, alerts, and more
npm MIT -
Read-only Prometheus/Thanos MCP server for metrics querying, cardinality analysis, and monitoring
pypi MIT -
MCP server for Prometheus — metrics query, range queries, alerts, targets, metric discovery
pypi MIT -
Enable AI assistants to query Prometheus using natural language. Discover metrics, analyze performance, and get insights — no PromQL required. Powered by Model Context Protocol (MCP).
npm MIT -
Prometheus MCP server — free PromQL metrics store so Claude and ChatGPT can query your observability data
MIT -
MCP server for generating Grafana dashboards and Prometheus alerting rules from application metrics
npm MIT -
prom-mcp-servergithub.com/ives22/mcp-toolsupdated this year
MCP Server for Prometheus monitoring - query metrics, alerts, targets via natural language
pypi MIT -
@peachjed/mcp-prometheusupdated this year
MCP server for Prometheus — query metrics, inspect alerts and rules from Claude
npm MIT -
A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.
pypi MIT ★ 526 -
Read-only Prometheus tools for any MCP client: find metrics, run PromQL, check targets and alerts. LLM-friendly summaries.
MIT -
Find and cut cardinality in Prometheus and Loki. See which jobs, metrics and labels drive your series and log streams, then export relabel, Alloy or Adaptive Telemetry rules. MCP-ready.
★ 1 -
Self-hostable Linux and edge fleet-management platform — operate machines behind NAT and firewalls with a WireGuard mesh, remote commands, SSH proxying, Prometheus metrics, events, and MCP over one API.
NOASSERTION ★ 25 -
prometheus-remote-mcp-CDKgithub.com/MohamedSherifAbdelsamiea/prometheus-remote-mcp-CDKupdated this year
Production-ready Prometheus MCP server deployed as AWS Lambda with API Gateway and Cognito OAuth. Provides 5 Prometheus tools (workspaces, queries, metrics) via secure HTTP endpoints. CDK deployment creates 3 stacks, generates client config. ~$5-10/month cost. Quick deploy with npm install && cdk deploy --all
MIT-0 -
observe-mcp-servergithub.com/zhangrj/observe-mcp-serverupdated this year
A MCP server that support Prometheus metrics, Openobserve logs and Skywalking traces
GPL-3.0 -
Prometheus MCP server for AI agents: query metrics, explain firing alerts, discover series (Claude Code, Cursor, any MCP client)
mcpb MIT -
Kairos is a self-hosted uptime and availability monitoring application. It periodically checks whether your HTTP services, Docker images, and TCP endpoints are reachable, can discover Docker images from repository prefixes, stores a full check history, and presents the results on a clean status dashboard or as prometheus metrics.
AGPL-3.0 ★ 2 -
ClaudeScalegithub.com/kratosvil/ClaudeScaleupdated this year
Intelligent Kubernetes scaler powered by Claude AI via MCP — monitors Prometheus metrics and auto-scales deployments in real time
MIT -
stlouis-pollengithub.com/pmaxhogan/stlouis-pollenupdated this year
St. Louis County pollen & mold — JSON API, Prometheus metrics, and no-auth MCP server with history back to 2000. Cloudflare Worker.
MIT -
Self-contained MCP server for hybrid document search (BM25 + dense RRF) — retrieval-only, works out of the box, Prometheus metrics, Docker, CI/CD
MIT -
otel_prom_mcp_servergithub.com/fabriciodf/otel_prom_mcp_serverupdated this year
Prometheus AI Lab is a Dockerized playground with Prometheus, OTel Collector, a demo FastAPI emitting OTLP metrics, a PromQL UI that uses Ollama’s Llama3 to turn natural language into queries, and an MCP server already pointed at Prometheus. Spin it up, pull the model, and explore metrics end-to-end with raw JSON and human-friendly summaries.
★ 1 -
WispMQ — an MQTT v5.0 / v3.1.1 / v3.1 broker in Rust (Tokio + SQLite): TCP/TLS/mTLS/WebSockets, auth + ACLs, Prometheus metrics, MCP.
Apache-2.0 -
Chat with your Docker host. An MCP server + interactive panel + terminal UI to manage Docker & Compose, with Prometheus metrics. By SoyRage Agency.
MIT ★ 3 -
Go-based Unraid plugin monitor and control your Unraid system via REST API, WebSocket, MCP, Prometheus, and MQTT. Supports Docker/VM control, real-time metrics, Home Assistant integration, and AI agent tooling.
MIT ★ 76 -
Grok 4.5 MCP server with chat, web/X search, model management, rate limiting, caching, and Prometheus metrics.
-
grafana-observer-mcpgithub.com/ankitpro/grafana-observerupdated this year
MCP server for observing Grafana dashboards, panels, and querying Prometheus metrics
npm Apache-2.0 -
营销文案事实审校与视频合成 Agent:Qwen 经 MCP 检索资料逐句核查,缺证据即停止;5 种检索策略 Hit@5 10%→43.3%,4B/14B 对照留出集 75%→100%;148 测试、OTEL/Prometheus 可观测、人工确认绑定快照后渲染 FFmpeg 视频。 | Marketing fact-checking agent: Qwen retrieves evidence over MCP, refuses unsupported rewrites; 5 retrieval strategies, 4B/14B comparison, 148 tests, OTEL metrics, version-bound approval, FFmpeg rendering.
MIT ★ 1 -
Stratus-MCPgithub.com/FilipooSVK/Stratus-MCPupdated this year
Kyronix Stratus NTP MCP is a read-only Model Context Protocol server for diagnosing and monitoring a Stratus NTP node backed by Prometheus metrics.
MIT ★ 1 -
Edge-native uptime monitor built with Remix 3 on Cloudflare Workers. Multi-region checks, status page, Prometheus metrics, MCP server.
★ 1 -
mirugithub.com/ConeDjordjic/miruupdated this year
A local MCP server that gives LLMs direct read access to Grafana Loki logs and Prometheus metrics
cargo Apache-2.0 ★ 1 -
Turn your Readwise library into a blazing-fast, self-hosted semantic search engine – complete with nightly syncs, vector search API, Prometheus metrics, and a streaming MCP server for LLM clients.
MIT ★ 24 -
DMARC aggregate report parser with a built-in dashboard. One Go binary, IMAP in, SQLite, Prometheus metrics, MCP server. Apache-2.0.
go Apache-2.0 ★ 233 -
把 RAG 检索能力封装成标准 MCP Server:用 Python + 官方 MCP SDK(stdio 模式)把一套 RAG 检索链路暴露成标准 MCP 工具,Claude Desktop、Cursor 或任意 MCP 客户端可直接调用;不依赖外部 LLM,装完依赖即可离线运行。除检索外做了生产化与安全加固:Bearer 鉴权、令牌桶限流、/healthz 只读快照、Prometheus /metrics 指标(零额外依赖)、检索结果的提示注入防护。
MIT -
@fluentcommerce/fluent-mcp-extnhttps://bitbucket.org/fluentcommerce/fluent-mcp-extnupdated this year
[Experimental] MCP (Model Context Protocol) extension server for Fluent Commerce. Exposes event dispatch, transition actions, GraphQL execution, Prometheus metrics, batch ingestion, and webhook validation as MCP tools.
npm MIT -
MCP-first toolkit for TypeSafe/Jev — the System One decision model. One stdio server (jev mcp) serves any MCP-capable harness, backed by one local event log and Prometheus impact metrics you can scrape into your own Grafana.
MIT ★ 1 -
mindcore-memory-mcpgithub.com/woshilaohei/mindcore-memory-mcpupdated this year
Production-hardened MCP memory server for AI agents: hybrid BM25+FAISS search, circuit breaker, SLO tracking, Prometheus metrics, BND boundary evaluation. Gives AI persistent long-term memory that survives across sessions.
pypi MIT ★ 1 -
remote-fs-mcp-servergithub.com/enclave-projects/remote-fs-mcp-serverupdated this year
Hardened SSH MCP server: 66 tools (file system, exec, SFTP, Docker, Git, network), audit log, Prometheus metrics, auto-retry, host-key verification, path allowlist, read-only mode. For Claude Desktop, Cursor, Kiro CLI, and any MCP client.
MIT -
IRIS_projectgithub.com/jordanaftermidnight/IRIS_projectupdated this year
IRIS — Integrated Runtime Intelligence Service. Multi-provider AI router with MCP server (13 tools), 16 providers (5 native + 11 OpenAI-compatible registry), council fan-out, batch APIs, circuit breakers, mTLS, mDNS, audit log, Prometheus metrics, 'iris provider add' CLI for any custom API.
MIT ★ 4 -
mcp-infra-livegithub.com/legacy-ai-labs/mcp-infra-liveupdated this year
MCP Infrastructure Live Production AWS infrastructure-as-code (Terraform + Terragrunt) that deploys and operates a live MCP server with a single command, EC2 running a Dockerized stack (PostgreSQL, NGINX), SSE/HTTP transports, Prometheus metrics, Route 53, and auto-renewing SSL, with a documented path from POC to production.
-
Secure Database MCP Server featuring a V8 Isolate Code Mode sandbox that unifies 181+ tools, delivering 70-90% token savings. Built for enterprise with HTTP/SSE transports, OAuth 2.1, dynamic filtering, granular RBAC, audit logging, deterministic error handling, Prometheus metrics, and encryption at rest for maximum observability and safety.
npm MIT ★ 13 -
🕷️ Turn PostgreSQL functions into a secure API: JSON-RPC, real-time SSE from LISTEN/NOTIFY, file & ZIP downloads, OpenAPI and MCP for AI agents. Every request runs as a real database role (GRANTs, RLS), with Basic or JWT auth. Single Go binary, zero boilerplate, Prometheus metrics.
go MIT ★ 7 -
Prometheus MCP Server
npm MIT -
MCP server for Prometheus integration
pypi MIT -
Prometheus MCP Server - Direct Prometheus integration for AI agents via Model Context Protocol
MIT -
A Model Context Protocol (MCP) server that provides tools for interacting with Prometheus monitoring systems
npm MIT -
MCP server that lets an agent run allowlisted PromQL on Mimir and read Prometheus alerts.
MIT -
kpmgithub.com/hrodrig/kpmactive
🚀 Kubernetes Pods Metrics — sample to SQLite; analyze-local + recommend, capacity/TUI; optional notify/MCP/server charts
MIT ★ 1 -
Real-time monitoring, slowlog analysis, and audit trails for Valkey and Redis
pypi NOASSERTION ★ 1,314 -
workbuddy-grafanaactive
WorkBuddy connector for Grafana: inspect live observability data and make safe, reviewable dashboard changes via MCP
npm MIT -
Real-time and historical metrics for locally served LLMs (Ollama and vLLM) — dashboard, HTTP API and MCP server. One process, one SQLite file, never in the request path.
Apache-2.0 ★ 1 -
A comprehensive Kubernetes observability toolkit built on the Model Context Protocol (MCP) for Site Reliability Engineering.
★ 2 -
macOS Reminders server with GraphQL, MCP, and metrics
MIT -
mcp_knowledge_servergithub.com/zachhew/mcp_knowledge_serverupdated this year
Production-oriented MCP-style FastAPI backend with typed tools, API key auth, scopes, audit logs, PostgreSQL search, Redis, metrics and CI.
MIT ★ 1