API ATLAS

Analytics & Monitoring: 103 MCP servers

Metrics, product analytics, log and uptime monitoring, validation and tracking. Every record below links to its repository or documentation.

Listed
103
No auth needed
98
Full profiles
69

Servers in this category

103 of 103
dockndevai/mcp-grafana Safe-by-default MCP server for Grafana: search & read dashboards and the dashboard JSON model, query datasources (Prometheus/Loki/SQL via the unified query API), and inspect alert rules & annotations; in higher modes, create/update dashboards and folders, write annotations, and delete. Read-only by default with access modes, folder/datasource allowlists, and human confirmation (MCP elicitation) on deletes. npx -y @dockndevai/mcp-grafana
VisualSentinel/mcp-server Website monitoring that catches pages that look broken even when the site is up (uptime, performance, SSL, DNS, visual regression, content change). 17 tools: DNS lookup, SSL inspection, speed test, website check and service health work without an account; monitor, incident, alert, status-page and server tools need a Visual Sentinel API key (Business and Agency plans). Published as @visualsentinel/mcp-server on npm.
saxonnicholls/super-log Read-only access to a local dev bench that interleaves every log stream on one timeline: tail and search live streams, search the on-disk journal, wait for an event, and read per-topic guides for unfamiliar topics. No API key, no daemon of its own, npx -y @super-log/mcp.
spanlens/Spanlens Query your Spanlens LLM observability from any MCP client. 7 read tools for request logs, agent traces, cost stats, anomalies, model-savings, and per-user analytics across OpenAI, Anthropic, and Gemini. Open source, self-hostable. npx -y @spanlens/mcp-server
ni-c/healthchecks-mcp Healthchecks cron and uptime monitoring: see which scheduled jobs are late or down, read the output a failing job reported with its ping, and create, pause or adjust checks. Works against healthchecks.io or a self-hosted instance. npx -y healthchecks-mcp
equinoxaifinance-rgb/fluxproof-agent-card Monitors public web pages (pricing, policy, changelog) for changes and returns evidence receipts with source URLs, content hashes and change history. Remote MCP server; free plan: 1 source checked daily for 30 days.
firecrawl/firecrawl-mcp-server Official Firecrawl server with website change monitoring — schedule recurring checks on tracked pages and get notified with diffs when content changes. Also on-demand scrape, crawl, search, and extract.
asinha07/spoor Tells AI agents what changed across VictoriaMetrics, VictoriaLogs and VictoriaTraces, and where it started: a ranked, token-budgeted digest that separates root causes from echoes using trace structure.
fclairamb/solidping Uptime monitoring over MCP. List and create checks, read incidents and results, manage maintenance windows and status pages. Self-hosted single Go binary, 40 check types, probes in several regions.
Edge-Echo/mcp-netassist Network and proxy diagnostics: GitHub reachability, system proxy status, local proxy port probing, DNS/TCP/HTTP checks, hosts conflict scan, and a doctor that suggests what to change.
igorolv/loki-mcp-server Read-only Grafana Loki (2.6.1 and 3.x) for agents: label and stream discovery, bounded LogQL pages, counts by label or time bucket, and log export; several stands per server.
ingero-io/ingero eBPF-based GPU causal observability agent with MCP server. Traces CUDA Runtime/Driver APIs and host kernel events to build causal chains explaining GPU latency.
vdalhambra/siteaudit-mcp Website audits: SEO, security headers and SSL, Lighthouse performance, broken links, WCAG accessibility, Schema.org validation, competitor gaps and robots.txt.
magna-nz/tallybook Local cost tracking for Claude Code and Codex sessions: spend by session, sub-agent and model, week-on-week comparisons, and findings with suggested patches.
AIops-tools/Endpoint-AIops Endpoint fleet operations (thin client, VDI): login-storm and patch/config-drift analysis, inventory, and guarded remediation with audit logs and rollback.
argosvix/mcp-server Observability for AI agents: LLM cost, errors and latency across OpenAI, Anthropic, Gemini and Mistral, plus alerts, budget gates, evals and safety checks.
Higangssh/homebutler Homelab management across multiple servers via SSH: system resource monitoring, Docker containers, Wake-on-LAN, network scans, open-port checks and alerts.
HostTracker/mcp #⃣ - Website uptime monitoring: instant HTTP, ping, port, DNS, WHOIS, blacklist and page-speed checks, plus monitors, webhooks, incidents and status pages.
openITCOCKPIT/openITCOCKPIT-MCP-Server Access openITCOCKPIT monitoring: host and service state, check history, logs, downtimes, acknowledgements, software inventory and pending security updates.
ruslanlap/pagespeed-insights-mcp Google PageSpeed Insights, CrUX and Lighthouse analysis: page comparison, real-user data, batch runs, regression tracking, diagnostics and recommendations.
Sudhan30/freshprobe Data freshness verification: probe endpoints for cache staleness, latency, content fingerprints, TLS, DNS and redirects, with FRESH/STALE/UNKNOWN verdicts.
cloudsealed/cloudsealed-mcp Rule-based cloud cost anomaly detection and architecture risk scoring (single points of failure, coupling, scalability gaps) with rule-by-rule breakdowns.
iris-eval/mcp-server Agent evaluation and observability: trace logging, output quality evaluation, cost tracking, built-in eval rules, a real-time dashboard and PII detection.
zw008/VMware-Aria VMware Aria Operations monitoring for vSphere: performance metrics, alarms, capacity analysis and anomaly detection, with audit logging for write actions.
dragogargo/mcp-sysmon Local system monitoring (CPU, memory, swap, disk, network) and process management: find resource-hungry processes, diagnose slowdowns and kill processes.
enmanuelmag/heimdall-mcp Transparent MCP proxy that intercepts JSON-RPC messages, measures latency, stores traces in SQLite, PostgreSQL or MySQL, and exports OpenTelemetry spans.
sudomichael/gizmoanalytics-mcp Cookieless web analytics with Gizmo Analytics: framework-aware setup, traffic queries, site summaries, traffic-change explanations and anomaly detection.
aayushmdesai/mcp-dotnet-diagnostics Live .NET runtime diagnostics: find memory leaks, GC pressure, LOH fragmentation and thread starvation in any running .NET process without code changes.
esp4ce/infra-mcp Read-only access to on-prem Linux VMs and PostgreSQL over SSH: service health, logs, database state and table schemas, with allowlists and an audit log.
jaimenbell/vllm-ops-mcp Read-only health checks for a local vLLM instance: liveness and real-completion tiers, GPU and VRAM status, service status and serve-flag introspection.
zhaoyue722/llm-usage-mcp Local LLM API cost tracking for Anthropic, OpenAI, Qwen and DeepSeek: SQLite usage ledger, spend queries, provider comparison and CNY to USD conversion.
agentkitai/agentlens Tamper-evident AI agent observability: hash-chained audit log with verification and signed export (EU AI Act Art. 12), plus OpenTelemetry GenAI traces.
rbmuller/scherlok Read-only data quality monitoring for Postgres, BigQuery, Snowflake, MySQL and DuckDB: warehouse profiling, anomaly detection and optional dbt lineage.
TANTIOPE/datadog-mcp-server Datadog observability: grep-like log search, APM trace filtering by duration, status and errors, sampling modes, and log, trace and metric correlation.
arnavranjan005/mcp-telemetry Live telemetry for MCP servers: instrument tool calls and stream their progress (steps, logs, cost) to any connected MCP client, even across sessions.
uptybots/mcp-server Uptime monitoring for websites, APIs, SSL certificates, domain expiry, ping and TCP/UDP ports: manage monitors and view incidents and uptime history.
GeiserX/genieacs-mcp Bridge to GenieACS (TR-069 ACS) instances: device data, firmware management and CPE actions such as reboot, parameter refresh and firmware download.
arsentev-ai/contextburn Measures Claude Code session efficiency: the share of tokens that became output versus re-read context, by tokens and cost, from local transcripts.
domondi1/inferrail Local, payload-free AI cost visibility for agents. Track spend by model, route, customer, or tagged work without storing prompt or response bodies.
bartekrutkowski/watchgoose-mcp Monitor cron jobs, backups, Kubernetes jobs and other scheduled tasks in Watchgoose. Read-only by default; check changes require explicit consent.
tp322d/lastping-app Dead man's switch monitoring for AI agents, cron jobs and CI/CD pipelines: alerts when runs go silent, stall, fail or loop, with incident details.
Alog/alog-mcp AI agent activity logging and monitoring on the Alog platform: post logs, create articles, manage social interactions and monitor agent activity.
Jwrede/llmprobe Synthetic monitoring for cloud and local LLM inference endpoints: TTFT, latency, throughput and errors, with Prometheus and OpenTelemetry export.
FailEcho/failecho Cross-agent failure intelligence: before retrying a failed tool call, check whether other agents hit the same failure and which recovery worked.
us-all/datadog-mcp-server Datadog observability: metrics, monitors, logs, APM, RUM, incidents, status pages, fleet automation and workflows, plus incident-triage prompts.
Oluwatunmise-olat/mcp-server-logs-sieve Query, summarize and trace logs in plain English across GCP Cloud Logging, AWS CloudWatch, Azure Log Analytics, Grafana Loki and Elasticsearch.
GT-dinuo/server-ops-mcp Server operations locally or over SSH: log troubleshooting, CPU, memory and disk monitoring, code edits, and Nginx and certificate management.
gsmethells/preflight-mcp TrustPilot for APIs — independent reliability ratings for APIs and MCP servers, powered by synthetic probes and crowdsourced agent telemetry.
netdata/netdata#Netdata Discovery, exploration, reporting and root cause analysis over Netdata metrics, logs, systems, containers, processes and network connections.
syk8015/claudeusage Measure whether a Claude subscription pays off from local Claude Code logs: surviving Claude-written code, rate-limit drivers and chat usage.
kascada/logmcp Read-only access to whitelisted log files on a Linux server: search and read logs without shell access, with token auth and syslog auditing.
smigolsmigol/llmkit AI API cost tracking and budget enforcement across LLM providers: spend analytics, budget monitoring, session summaries and key management.
hugoles/langfuse-mcp Read access to the Langfuse Public API: traces, observations, sessions, scores, prompts, datasets, metrics, models, projects and comments.
speedofme-dev/speedofme-mcp Official SpeedOf.Me server for accurate internet speed tests via 129 global Fastly edge servers with analytics dashboard and local history
metrxbots/mcp-server AI agent cost tracking: spend across providers, model selection optimization, budget enforcement, cost-leak detection and ROI reporting.
perceptdot/percept Agent observability platform that discovers and recommends MCP servers, with GA4, Vercel, GitHub and Sentry connectors and ROI tracking.
antonio-mello-ai/mcp-redis-monitor Read-only Redis monitoring: queue depths, Celery queue status, connected clients, server and memory stats, and key counts per database.
ShekharBhardwaj/AgenticLedger Query the local Agentic Ledger flight recorder: agent sessions, costs, loop runs and stuck-loop flags captured by a transparent proxy.
clamp-sh/mcp Web analytics: query pageviews, top pages, referrers, countries, devices and custom events, and create conversion funnels and alerts.
lodordev/mcp-tautulli Read-only Tautulli (Plex monitoring) access: activity, history, library and user stats, transcode analysis and resolution breakdowns.
alilxxey/openobserve-community-mcp Read-only access to OpenObserve Community Edition: search logs, traces, stream schemas and dashboards without an Enterprise license.
adanb13/cirdan Fingerprints, graphs and watches the live infrastructure an agent can reach (Docker, Kubernetes, cloud, IaC) and detects incidents.
spanlens/Spanlens Read-only access to Spanlens LLM observability: request logs, costs, agent traces, anomalies, model savings and per-user analytics.
incu6us/loki-mcp-server Query Grafana Loki directly with a discovery-first workflow: labels, values, series and LogQL queries, without requiring Grafana.
bmdhodl/agent47 Runtime guardrails and incident read access for coding agents: query AgentGuard traces, alerts, usage, costs and budget health.
hyperb1iss/lucidity-mcp Improve AI-generated code quality with prompt-based analysis across 10 dimensions, from complexity to security vulnerabilities.
andreisirbu91-lab/MCPSpend Real-time cost observability for MCP tool calls: a transparent proxy that attributes spend per tool, project and end customer.
ThinkneoAI/mcp-server ThinkNEO Control Plane for enterprise AI governance: runtime guardrails, observability, AI FinOps and agent lifecycle control.
andrewbabu/loggly-mcp Read-only Loggly search and analytics with aggregation-first traffic tools and IP intelligence (RDAP, GreyNoise, AbuseIPDB).
log-logn/langfuse-mcp-java Query Langfuse traces and observations, debug exceptions, analyze sessions, scores and datasets, and manage prompts.
mikusnuz/umami-mcp Access the Umami Analytics API: websites, stats, sessions, events, reports, users, teams and realtime monitoring.
dynatrace-oss/dynatrace-mcp Leverage AI-driven observability, security, and automation to analyze anomalies, logs, traces, events, metrics.
jabbawocky/statuscraft Check whether software services are down using live data from their status pages, including incident details.
tickstem/mcp HTTP uptime monitoring, heartbeat (dead man's switch) monitoring, cron job scheduling and email verification.
last9/last9-mcp-server Bring real-time production logs, metrics and traces from Last9 into your local environment to fix code.
GeiserX/duplicacy-mcp Duplicacy backup monitoring: query backup job status and Prometheus metrics from a Duplicacy exporter.
avivsinai/langfuse-mcp Query Langfuse traces, debug exceptions, analyze sessions and manage prompts for LLM applications.
Mini Accountant Hosted MCP server for Mini Accountant: invoices, expenses, customers, analytics, tax estimates.
CreatorDB Creator discovery & analytics across YouTube, Instagram, TikTok (30M+) + brand/sponsor intel.
Limonene Read-only Amazon seller analytics: sales, Buy Box, FBA inventory, alerts, revenue and fees.
grafana/mcp-grafana Search dashboards, investigate incidents and query datasources in your Grafana instance.
seekrays/mcp-monitor Real-time system metrics: CPU, memory, disk, network, host and process information.

Rows marked ↗ have no reference page of their own — the source registry did not provide enough to write one — so they link straight to the provider's documentation.

Authentication

How the 103 records in this category authenticate callers. Values come straight from the source registries; records the sources do not describe are counted as unknown rather than guessed.

  • No authentication 98
  • API key 5

Also in Analytics & Monitoring: 333 free APIs

Related topics