MCP servers for monitoring and observability
Observability servers let the AI tool read logs, metrics, traces and alerts while it investigates an incident or a slow endpoint, instead of you pasting them into the chat. Most of them connect to a hosted monitoring service and ask for a token with read access to it. The list is ranked by GitHub stars; servers without that figure come after the ranked ones.
MCP servers for monitoring and observability
Ranked by Stars (GitHub). Figures of different marketplaces are never added up.
-
Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
GitHub stars: 80 889 -
Manage monitors, status pages, incidents and maintenances in your openstatus workspace.
GitHub stars: 9 177 -
mcp-grafana io.github.grafana/mcp-grafana
An MCP server giving access to Grafana dashboards, data and more.
GitHub stars: 3 549 -
Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
GitHub stars: 1 459 -
monitor io.github.BetterDB-inc/monitor
BetterDB MCP server - Valkey observability for Claude Code and other MCP clients
GitHub stars: 1 307 -
Sessy — Amazon SES observability
Read-only Amazon SES observability: search events, inspect bounces, pull delivery stats.
GitHub stars: 939 -
sentry-mcp io.github.getsentry/sentry-mcp
MCP server for Sentry - error monitoring, issue tracking, and debugging for AI assistants
GitHub stars: 925 -
Runtime-level MCP server for Phoenix development: run code, read logs, query the DB, read docs.
GitHub stars: 855 -
MCP server providing Prometheus metrics access and PromQL query execution for AI assistants
GitHub stars: 518 -
Persistent agent memory as a single Go binary: knowledge graph, TUI observability, zero infra.
GitHub stars: 481 -
Runtime-level MCP server for Rails development: run code, read logs, query the DB, read docs.
GitHub stars: 476 -
Compress logs, retrieval chunks, and code context into structured LLM-ready signal.
GitHub stars: 329 -
ditto io.github.ohad6k/ditto
Mine your local AI coding session logs into a profile your agent loads before every task.
GitHub stars: 294 -
emulo io.github.ohad6k/emulo
Mine your AI coding session logs into a you.md profile with dated receipts, for an agent to read.
GitHub stars: 294 -
Read-only MCP server for CortexPilot workflows, queue state, proof, replay, and incident summaries.
GitHub stars: 207 -
Read-only MCP for OpenVibeCoding runs, workflows, proof, queue, replay, and incident reads.
GitHub stars: 207 -
Query your Betterlytics web analytics from AI agents: traffic, funnels, journeys, errors, uptime.
GitHub stars: 178 -
lastsaas io.github.jonradoff/lastsaas
Read-only admin MCP server for LastSaaS — dashboards, users, tenants, billing, logs, health.
GitHub stars: 173 -
mcp-ts-template io.github.cyanheads/mcp-ts-template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
GitHub stars: 152 -
Self-hosted team docs with live Prometheus charts. Read, write and query your docs over MCP.
GitHub stars: 148
How the list is built
- Type: MCP servers.
- Category: Monitoring and observability.
- Ranked by Stars (GitHub); plugins without this figure come after the others and are marked, never shown as zero.
- GitHub figures rank a plugin only when its repository holds no other plugin we track; the figure of a shared repository is shown as the whole repository's and does not rank.
- Archived plugins are left out: an archived repository, or a marketplace that marks the plugin archived.
- Only known plugins whose page we index: listed on a curated marketplace or on two marketplaces or more, or with at least 50 stars on GitHub (of its own repository), 500 installs on Claude Marketplace or 5 000 pulls on Docker Hub.
- The list shows up to 20 plugins and is offered to search engines only with 8 or more.
The list is rebuilt from our latest passes. Nobody pays to appear in it or to rank higher.
All AI tool plugins · AI tool plugin statistics
Where the data comes from: how the catalog is built