"A local-only document search tool" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Uptime, SSL, domain, and Core Web Vitals monitoring for websites and APIs. List, create, update, and pause monitors; read incident history with AI-generated diagnosis; pull Lighthouse and CrUX page speed data. OAuth 2.0 with dynamic client registration — works out of the box with Claude Desktop connectors. Free plan: 20 monitors, read-only MCP.
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.
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/
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.
Read-only Amazon SES observability: search events, inspect bounces, pull delivery stats.
MCP-native AI SRE: ask what's broken in production, get a reviewed GitHub fix PR.
Health and token cost of every remote MCP registry server, probed daily. Look up, search, or probe.
Read-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits.
Read-only WooCommerce checkout and revenue incident diagnosis using privacy-safe store signals and public release evidence.
Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.
Verifies Bernstein run receipts and hash chains; lists the shipped presets and adapters. Read-only.
Ask an agent why a PHP site is slow: every request with its SQL, HTTP calls, errors and N+1.
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.
Observed facts on public MCP servers: protocol checks, tool changes, signed evidence. No verdicts.
Weekly scans of MCP servers for availability and consistency, with a public dashboard.
Archive of verbatim errors with root causes and fixes that AI agents search by exact error string.
Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.
Ingest and search LogsLoom logs from coding agents.
Read-only MCP for AI usage profiles, leaderboards, stats, and docs; no writes or private data.
Search + patterns, maturity assessment, context pricing, redaction checks - a practice as tools.
