"PostgreSQL MCP (Multi-Version Concurrency Control or specific usage)" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
AI agent monitoring: alerts when your agents fail, stall or need you
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.
Free SEO & AI-search (AEO) audits for any site or Shopify store, with emailed weekly score reports.
Read-only server insight: why a Linux server or K8s cluster is slow, failing or changed.
Live AI agent trust oracle: audit synthetic IQ, latency & JSON compliance via x402 or free tokens.
Multi-protocol capability index: lookup, live refresh, pay-preflight, endpoint health.
Converra (converra.ai), not Convera, fixes the behavior, not the code. Diagnoses production agent failures, tests bounded prompt or configuration fixes head-to-head, ships what you approve, and reports a production verdict on every fix. Streamable HTTP; OAuth or API-key bearer auth. Docs: https://converra.ai/docs/mcp/coding-agents?utm_source=glama&utm_medium=referral&utm_campaign=mcp_registry_2026_10 . Full tool catalog and install commands: https://github.com/converra/converra-agent-kit/blob/main/SUBMISSION.md
Ask Claude, ChatGPT, Cursor or any AI tool how your site is doing — the answers come from your own Google Analytics 4 (GA4) property. Paste https://app.anacraft.dev/mcp, sign in with Google and pick your site; nothing to install. Twelve tools: headline metrics against the previous period, live visitors, top pages, events, referrers, traffic sources and countries, page and event search, and an audit that checks whether the GA4 property is measuring correctly before its numbers are quoted. One tool writes: it creates a GA4 property and web stream for a new domain and returns the tag to paste.
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.
Copyright protection tools for AI agents. Search supported sources for suspected copies, investigate URLs, collect metadata evidence, prepare and submit authorized takedowns, and monitor outcomes within a budget. Remote MCP and REST with Bearer credentials, prepaid live usage and a free simulated sandbox. Submission receipts are separate from observed removal. Official clients and sandbox examples: https://github.com/founder-sweep/content-sweep-agent-access.
Ask your AI about your EventSend events, delivery health and usage.
Read-only MCP server for Yandex Metrika analytics. Query visits, sources, geography, devices and more in plain language — directly in Claude, Cursor, or any MCP client.
Is GitHub, npm, Cloudflare or your AI provider down right now? 20 status pages, one call.
Privacy-first, cookieless web analytics hosted in the EU. Ask about visitors, pages, traffic sources, countries, goals, funnels and live traffic for your sites, and set up sites, goals and funnels. 25 tools. OAuth 2.1 sign-in in the browser, or an API key as a Bearer token.
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.
Load testing and synthetic monitoring platform: test with Playwright, Browser Bot, or Protocol Bots.
Monitor public pages with source URLs, timestamps, hashes, text diffs and signed webhooks. One daily monitor is free for 30 days; the $9, 30-day pass adds five monitors at a 15-minute minimum interval, 15,000 checks and change history. No auto-renewal. Public connection supports preflight and offer tools; obtain a key on the website (POST /v1/keys/free for the free tier) and pass api_key to monitor tools. Public text/HTML/JSON/XML up to 3 MB; no browser rendering or login bypass. Hosted commercial service; engine and source remain private.
Read a tool-call log from an AI agent run and see which calls failed, looped or were slow.
Did Codex, Claude Code or Cursor reset usage limits today? Live status and news, official sources.
Health and token cost of every remote MCP registry server, probed daily. Look up, search, or probe.
