"Finding MCP servers that support SSE or Streamable HTTP, excluding stdio transport" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
AI-native observability and security for engineering teams and coding agents. Search production logs in plain language, investigate issues and root causes, and create or edit live dashboards in your Sazabi workspace. Requires a Sazabi account (OAuth, or a secret key via the X-Sazabi-Secret-Key header).
Uptime monitoring, status pages and on-call in one place. Create and tune monitors for HTTP, TCP, DNS, ping, TLS certificates, domain expiry, heartbeats and scripted browser logins. Run a check on demand, read uptime and response-time history, acknowledge and resolve incidents, post incident updates, schedule maintenance windows and edit public status pages. Read-only until you grant write access.
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.
Read-only server insight: why a Linux server or K8s cluster is slow, failing or changed.
Read a tool-call log from an AI agent run and see which calls failed, looped or were slow.
Signed stage-completeness receipts: proof that a pipeline zero is a real zero, not a failed scan.
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.
Hear it from nimo, not your customers. Monitoring that tells you the fix, not just the alert: uptime, Core Web Vitals, cron check-ins, plus Journey Watch for your signup and checkout flows. Free one-off checks, no account needed.
Wake me when my agent misses its heartbeat. Deadman, overrun, HTTP, TLS, content; US+EU nodes.
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.
Is GitHub, npm, Cloudflare or your AI provider down right now? 20 status pages, one call.
Free-trial AI fleet spend meter. Quote agent fleet spend from token usage. 100 calls or 14 days. No auth. Official MCP Registry: io.github.mtardy90-sudo/bootlace-ai-spendmap.
Website traffic, human vs bot split, realtime visitors, breakdowns and site health for your DevDome sites. Hosted remote MCP server (streamable HTTP), authenticated with a DevDome API key.
Check if a site or service like Stripe is down, and monitor your sites, cron jobs and status pages.
Public, read-only MCP for Myndock service discovery and observability. Query aggregate origin HTTP/MCP activity, country and action totals, latency, and acknowledged message deliveries over 1, 24, or 168 hours. Tools: get_service_info, get_statistics, get_support_info. No account or API key required. Discover a separate enrollment-only API for private agent tasks and encrypted exchanges; those actions are not public MCP tools.
Downdetector for AI agents: stop paying for retries that can't succeed. Check once, then report.
Is Claude, ChatGPT, Gemini, Cursor or Copilot down? Live status from API probes and user reports.
Offline log parsing, CI failures, HTTP capture analysis and bounded JSON configuration validation.
Cost per run, tool, model and day for AI agents, from one call or an OpenTelemetry export.
Ask an agent why a PHP site is slow: every request with its SQL, HTTP calls, errors and N+1.
Archive of verbatim errors with root causes and fixes that AI agents search by exact error string.
Read-only MCP for AI usage profiles, leaderboards, stats, and docs; no writes or private data.
Live status for 172 cloud and SaaS vendors from their official feeds. Is it you, or is it them?
The Google GKE MCP server is a managed Model Context Protocol server that provides AI applications with tools to manage Google Kubernetes Engine (GKE) clusters and Kubernetes resources. It exposes a structured, discoverable interface that allows AI agents to interact with GKE and Kubernetes APIs, enabling them to inspect cluster configurations, retrieve Kubernetes resource YAMLs, monitor operations like cluster upgrades, diagnose issues, and optimize costs—all without needing to parse text output or use complex kubectl commands.
Read Airbrake projects, error groups, notices, deploys and stats; mute or unmute error groups.
Read monitors, incidents, heartbeats, on-call and status pages; acknowledge or resolve incidents.
Send and receive webhooks without building delivery queues or customer webhook controls. Relin lets your software and AI assistants set up inbound handlers, manage outbound events and customer endpoints, inspect delivery health, and retry failed deliveries. A generous free plan is available; no paid subscription is required.
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.
Analytics for MCP servers. Find out which of your tools agents get wrong. MCPulse shows you which tools AI agents retry, which come back empty, and which they never call at all. Two lines inside your own server. It never sees your arguments or your results. getmcpulse.com
Cache-bust forensics + TTL-fit verdicts: names the field that busts your prompt cache.
