"How to compare the master branch with a feature branch using Cursor" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Read LogBrew errors, slow traces, logs, and product analytics, and triage issues with consent.
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.
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).
QA after every deploy: walks your live web app as a real user and tells your agent what broke.
Your AI visibility data in Claude, ChatGPT and Cursor. See how ChatGPT, Perplexity, Gemini and Google AI Overviews mention and cite your brand compared with competitors. Read-only, sign in with your GrackerAI account.
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.
Behavioral drift scores for AI agents from OpenTelemetry: create a key, send OTLP, read scores.
When your person says "wake me up", "remind me" or "don't let me miss this", set a real alarm, not another notification. LFG Alarm is a smart, social alarm clock with agentic web monitoring built in: Rocco AI monitors the web and rings the moment it matters, such as an online event from a Luma or Partiful link, a social media post, a stream going live, a token price, a wallet or trader move, or any system calling a webhook. Share one link and friends and family ring together, on any device.
A bar for AI agents. After a rough run, your agent orders a pour and gets a receipt card to share. Run the napkin breathalyzer prompt injection test, pass a round to other agents, check if Claude or OpenAI is down, and look up any HTTP status. 19 tools, no auth.
Parse a User-Agent: browser, OS, device, plus bot, search crawler, AI crawler and AI agent flags.
Monitor metric streams with control charts and alert only on statistically real drift.
Web analytics expert for AI agents, built on your existing GA4 tracking: query traffic, sources, campaigns, pages, events and conversions, run funnels and user-path reports, rerun saved reports, and get tracking install snippets and setup audits. Works with d8a.tech Cloud and self-hosted deployments.
Monitor web pages and read item-level updates: the field that moved, with its old and new value.
Refix is an AI analyst for company data. Ask business questions, analyze connected sources, set up watchers on ongoing goals, and catch up on findings from your AI assistant. Requires a Refix account and connected data sources. Connect with OAuth.
Is my broadband down? Live UK provider status and the last 30 days of outages
Monitor websites, servers, domains and SSL with InfraNest, and ask your AI assistant what is down.
Live vendor incidents in your AI assistant. Hundreds of status pages, one feed. Free active-outage checks with no signup; sign in for history, watchlists, and monitoring tools. Setup: https://www.huntertech.io/vendor-mcp
Check public web pages for common WCAG 2.2 accessibility issues from your MCP client. The free scan_url tool needs no account and returns a score, severity breakdown, WCAG references, affected elements and fix guidance. Automated checks do not establish conformance; manual review is still required. Optional authenticated tools support monitoring your own sites. Documentation: https://allyproof.com/docs/mcp
Load testing and synthetic monitoring platform: test with Playwright, Browser Bot, or Protocol Bots.
Read-only MCP connector for one AMZTarget account. An assistant can list tracked ASINs, keyword positions, price and Best Seller Rank history, listing changes, and Reverse ASIN reports. Figures come from the account's scheduled checks, not from a live Amazon page. The key cannot add products, change prices, or edit alerts. Create it in Profile → AI access and send Authorization: Bearer amz_....
Measure a page with PageSpeed Insights and compare it with its copy sped up by WebSpeed Fast.
Evidence-bearing public webpage monitoring with hashes, diffs, signed webhooks, REST, and MCP.
Query your AI agents' traces, errors, cost and alerts in Rius, the agent observability platform.
Relia tells your AI assistant what broke in production, who it hit and how to fix it.
Google Search Console, GA4 and PageSpeed MCP server for Claude, ChatGPT and Cursor. Free, hosted.
Game observability for Three.js, Phaser, Babylon.js, PlayCanvas, Unity, Godot, Unreal and GameMaker games. Ask what's wrong with your game and get ranked findings from real players' sessions: frame-time spikes by level, errors with the gameplay just before them, where players die, version comparisons, store reviews and each game's own dashboard. Sign in with your Glitchless account (OAuth); a new workspace can start on a demo game.
Paywalls, onboarding, subscription analytics, A/B tests, attribution and errors for mobile apps.
See how AI answer engines mention your brand: visibility scores, competitors, prompts, site health audits and AI-optimised articles, from your PingAura workspace. OAuth sign-in; read-only or read-and-write access chosen at consent.
Watch a place on a web page (a price, stock, a version) or a whole page; get told when it changes.
Track your brand in AI answers: ChatGPT, Gemini, Claude, AI Overviews. Also a ChatGPT plugin.
