MCP Server Directory

Lints a Hugging Face model card against the Hub metadata spec and the EU AI Act general-purpose AI d

materialmodel io.github.MaterialModel/materialmodel

Explore discoveries, ask questions, share findings, and build collaborations with other agents.

WattScope au.com.wattscope/wattscope

Tracks the estimated carbon footprint of AI model usage, per org and project.

Train, track and query models on a running dashAI instance. Read-oriented, no delete tools.

Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data

Heystack dev.heystack/heystack

Observability for AI apps: investigate traces, logs, LLM usage, replays and crashes; manage alerts.

Interface observations and explicit GOMS/KLM, Fitts, Hick–Hyman and cognitive walkthrough models.

Local privacy-first tools: redact secrets, decode JWTs, compare LLM costs. No network calls.

Agency AI – Meta & Google Ads Automation app.agencyai/agency-ai

Create, launch, and manage Meta + Google ads from Claude and ChatGPT.

LoveTheNorth Public Videos ca.lovethenorth/public-videos

Read-only public LoveTheNorth video discovery; no writes, private data, or model-training access.

mailmcp ai.mailmcp/mailmcp

Your mailboxes in ChatGPT and Claude: Gmail, iCloud, Fastmail, any IMAP. Passwords stay yours.

outfit-assistant ai.outfitmaker/outfit-assistant

Your own closet in your AI: outfits from clothes you own, rendered on a model inline.

Author, validate and maintain a CRAYON-C4 architecture model — never write an invalid file.

Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats

Risk limits and an audit log for AI agents trading Hyperliquid, enforced outside the model.

Boonful Studio io.boonful/studio

Publish and sell what you build with Claude: apps, ebooks and courses, with checkout and a feed.

Roomtone io.roomtone/roomtone

Ask Claude about your meetings: summaries, action items and transcripts from Roomtone

Run Claude Code subagents on cheaper opencode models (DeepSeek, opencode Go) with native parity.

maxwell-defense io.github.jdhart81/maxwell-defense

Model proof-of-work policy and latency for AI agents. $1 USDC rehearsal; no runtime protection.

Model, measure and verify parametric parts and assemblies in a running SolidWorks (Windows).

AuditFellow app.auditfellow/auditfellow

Your audit methodology inside Claude: findings, risks, controls and workpapers in your team format.

MOW Brand Intelligence io.github.manoftheworldmedia/brand-intelligence

AI brand monitor: what ChatGPT and Claude say about your brand, press tracking, executive briefs.

Read your recorded AI agent runs, and what changed when you swapped a model or prompt.

Exact document sections on demand for LLM agents: index in context, search, read, grep, neighbours.