PGYER
Local installio.github.PGYER/pgyer-mcp-server
Upload Android, iOS and HarmonyOS apps to PGYER and manage their apps and versions.
Live AWS, database & Kafka infrastructure context for AI coding assistants via MCP.
SEC EDGAR in 22 tools: 10-K/10-Q/8-K text, XBRL facts, insider trades, 13F, full-text search.
Real Chromium browser for AI agents: compact outlines, diff-only replies, real input, you approve.
F1 race analytics & live timing for AI assistants — webhooks, results, and session replays.
Local-first AI identity for MCP coding tools. Lessons, decisions, and context you control.
Read and write Slack with session tokens — no OAuth, no bot, no admin approval.
Safe-by-default UniFi MCP: Network + Protect + Access, multi-site, dry-run, audit log.
WCAG 2.1 AA accessibility scanner (Playwright + axe-core) with grounded, browser-verified fixes.
Visual website feedback, screenshots and team discussion for coding assistants. Self-hosted.
Let agents use temporary secrets without receiving their values in chat. Local stdio; Node 22+.
Run Android tests on real phones, or lease one: install, shell, screenshot, logcat.
LSP call graph for coding agents: a symbol's callers, callees, tests and live files in one call.
Screen a name vs Nigeria's NIGSAC sanctions register. Best-effort signal. A Wycord product.
Delegate coding tasks to the OpenAI Codex CLI, installed separately, with explicit model and effort.
Kiln MCP server for agents: design, slice, print, monitor, and recover physical objects safely.
Live Google search results, domain positions and open markets via the Serper.live SERP API.
Tells coding agents which npm dependencies changed after their training cutoff, and what changed.
Production IMAP & SMTP for Claude: multi-account email search, triage, send, and spam checks.
Exposes the full Qdrant vector database API as 56 MCP tools, not just store/find.
Serial terminal with a GUI that AI assistants drive over MCP: read device logs, send commands.
REAPER MCP server: let Claude read your session, set FX, write automation and measure mix moves.
Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
Validate XRechnung XML and ZUGFeRD / Factur-X PDFs with the free checkxrechnung.com API.
Run Scout Monitoring's MCP tools locally with an API key: endpoints, traces, errors, N+1 insights.
Annotated screenshots for AI agents: steps, Skitch-style arrows, boxes, labels, solid redaction.
Native WebKit for Mac. Human approval and persistent sign-ins. Requires the companion app.
Real-time UAE property, retail and travel data: listings, transactions, rental yields, products.
Route one agent through one MCP server to many, with progressive tool discovery to shrink context.