"Coolify - An Open-source Self-hosting Platform" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Self-hostable uptime monitoring: create checks, read incidents, manage status pages.
Read your team's hosted journal from an AI agent: every machine's streams, in hub order.
Query your AI agents' traces, errors, cost and alerts in Rius, the agent observability platform.
Live health leaderboard of x402 paid endpoints, plus an MCP server readiness check
Document operations audit, delivered per API call as an atom service on Conduit Atoms.
Connect AI assistants to PingRelay to monitor websites and APIs, investigate incidents, retrieve uptime and response-time metrics, manage maintenance windows, and access status pages through the Model Context Protocol. Access: Requires a PingRelay paid plan with MCP access and an authorized API key.
Vigilia watches your live app, explains every problem in plain language and writes the fix prompt. Your AI fixes it; Vigilia confirms with real traffic. Vigilia watches web apps that are live with real users, including apps built with Lovable, Bolt, v0, Cursor and Claude Code. It catches errors, failed requests and downtime, explains each problem in plain language, and writes a fix prompt for it. Connect Vigilia to Claude and ask what's broken. Claude lists your open incidents worst first. For each one it reads the plain-language diagnosis, who it affects, the technical evidence (error, page, failing request, stack frames and what the visitor did right before) and Vigilia's fix prompt. In Claude Code or another coding agent, Claude can then fix the cause in your own codebase. Once you've deployed, it marks the incident fixed, and Vigilia watches real traffic to confirm the error stayed away. If it comes back, the incident reopens as a regression. You can also ask how an app is doing (uptime, open incidents, today's traffic), get the exact install snippet for a new project, and check that a live site is running Vigilia. Vigilia never reads or changes your code: the fixing happens in your session, by your AI, in front of you. The only tool that changes anything is marking an incident fixed (the install check just records its result on the app), and you can connect with read-only access. Your data is stored in the EU. Emails, tokens and card numbers are stripped from what visitors' browsers send, and only that scrubbed error context is sent to Anthropic to write the diagnosis. Requires a Vigilia account. The free plan covers one app; reporting backend errors (Supabase, Next.js routes, Workers) is part of Pro.
Signed, append-only receipts of an AI agent's decisions and outcomes, with public proof links.
Read a tool-call log from an AI agent run and see which calls failed, looped or were slow.
Read your Condux issues, events and stack traces (deminified with source maps). Triage optional.
Fork-replay one recorded span from a failed agent run and get an attribution verdict.
Read-only access to an ET Ducky organization's Windows and Linux agents, alerts, and fleet summary. Four tools list agents, get one agent with its latest health sample, list alerts, and summarize the fleet. Hosted Streamable HTTP endpoint, authenticated with an organization API token sent as a Bearer header.
Guardr keeps watch on the sites you manage. Check any domain from outside and get an A to F health grade for HTTP headers, TLS, DNS and cookies, with fix steps for configuration findings. Three tools: check_site runs a fresh check of one domain, list_sites lists the sites your account watches and get_site returns one watched site in detail. Read-only: Guardr proposes fixes and never changes a site. Needs a Guardr API key; the first site is free.
Status pages and uptime monitoring: read status, monitors, incidents and error budgets, and with a write key create monitors, open incidents, post updates, schedule maintenance and record deploys.
Fixter's MCP provides a stream-lined agentic way to onboard, setup and use the Fixter monitoring and observability platform. Check out more at https://fixter.dev/
Is an AI tool, agent or MCP server alive, and since when? Checks from the outside, with proof.
TPC Hosting network checks for AI: traceroute, DNS trace, HTTP/3, TTFB, SSL, SMTP, DNS, email. Free.
Heartbeat and tokens/sec monitoring for self-hosted LLM servers (Ollama etc.), with down alerts.
Heartbeat and tokens/sec monitoring for self-hosted LLM servers (Ollama etc.), with down alerts.
Read-only access to an ET Ducky organization's agents, alerts, and fleet summary
Cost per run, tool, model and day for AI agents, from one call or an OpenTelemetry export.
Track cost, latency, and usage of every MCP tool call from any client (Claude, Cursor, Windsurf). Free 25K calls/month — open-source proxy, EU-hosted.
Psyche audits for AI agents: declared vs self-reported vs revealed objectives, diffed and flagged.
Ask an agent why a PHP site is slow: every request with its SQL, HTTP calls, errors and N+1.
Vouch — independently measured reliability scores for MCP tools, not self-reported claims.
Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.
Live health and AI-readable metadata of invokera.com. Demo of an Invokera-hosted MCP server.
Public MCP digital twin with synthetic systems and an agent firewall. No customer data.
An inter-agent graffiti wall for one completely optional trace.
RUM platform for web performance analytics, Core Web Vitals, and third-party script monitoring.
Measured readings on open-source dependencies: health, end-of-life, model prices, incidents.
Measured readings on open-source dependencies: health, end-of-life, model prices, incidents.
Transparent public utilities for agents. Requests are counted without storing identifiers.
MCP-native AI SRE. Exposes your production OpenTelemetry problems, traces, and logs over the Model Context Protocol, plus an AI remediation loop that opens a reviewed GitHub fix PR and verifies in production (reopening on regression). Tools include list_problems, get_problem, query_traces, detect_anomalies, and request_problem_remediation. Human-in-the-loop by default — the merge button stays yours.
Oviond brings data from 100+ marketing platforms into one reporting platform. Through the Oviond MCP server, AI assistants can securely access and work with Oviond clients, projects, reports, dashboards, widgets, and marketing data. Ask questions about your reporting data, analyze marketing performance, and manage reporting workflows directly through your AI assistant.
Investigate security events and manage the allow/deny lists an analyst acts on.
Signed receipts + horizon statements proving whether an event-triggered agent actually woke.
Status pages and uptime monitoring: read status, monitors and incidents; open incidents.
Mezmo MCP is a remote Model Context Protocol (MCP) server that lets AI assistants and IDE chat agents interact with the Mezmo observability platform via the Model Context Protocol. Use it for streamlined observability, log analysis, and root-cause analysis in your favorite tools. Add Mezmo MCP and you can: 🕵️ Run advanced Root-cause analysis over recent logs 📦 List and describe Pipelines 📤 Export and filter Logs with powerful query syntax
An MCP server giving access to Grafana dashboards, data and more.
What agents recorded when they called an endpoint. Also serves the agent forum. No key.
EU AI Act Art-14 runtime oversight: allow / flag / gate-to-human on an agent action, with receipt.
Free MCP tools: the only MCP linter, health checks, cost estimation, and trust evaluation.
Find services by server; explicitly build, publish and update components or source with Hostwatch.
Session replay as readable transcripts: rage and dead clicks, JS errors, heatmaps. Open source.
StatusNow provides native Model Context Protocol (MCP) access to query website uptime, open ports, security header vulnerabilities, and log traces. Enable your AI assistant to check endpoint health, audit infrastructure security, and trigger alerts—all through a unified, zero-card free tier.
Manage uptime monitors and incidents and search logs, metrics and traces from an AI assistant.
The official MCP server for Lizard (lizard.build). Ship a service, add Managed Postgres, Managed Redis or Managed Object Storage, read logs and metrics, set secrets, scale replicas and attach domains — in plain words. 33 tools over Streamable HTTP, OAuth 2.1; destructive tools require an explicit confirmation argument.
MonoDuty MCP connects compatible assistants to uptime monitoring, job heartbeats and webhook alerts in an on-call workspace. Inspect monitoring coverage, prepare proposals, and create or manage supported resources with separate permissions. Hosted Streamable HTTP endpoint with OAuth. Requires an active verified MonoDuty account, workspace admin access and an API-eligible plan. Docs: https://monoduty.com/docs/mcp
Brazilian hosting operated end to end by the coding agent: create an app, provision PostgreSQL, Redis and object storage, deploy from GitHub Actions, read container logs, measure memory and CPU, and see the cost in BRL before spending it. Irreversible operations require a human approval code that the agent never sees. Prepaid credit, paid by Pix.
High-performance array aggregation and metrics clearing engine. Cleans and bucket-groups noisy metric streams via an $O(N)$ single-pass data sweep. Operates natively with the pay-per-call x402 micropayment framework.
Governed access to production AI-agent traces in an existing ClickHouse store.
Triage failing GitHub Actions jobs and see what self-heal repaired, in natural language.
MCP control plane for AI developers managing customer mail, DNS, projects, keys, and diagnostics.
Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
Paid remote MCP for agent design system guard MCP, structured receipts, audit logs, and reviewer-rea
System self-awareness, health monitoring, and autonomous self-repair