MCP Server Directory

Riv MCP server — a thin shell over the Riv authorization API (authorize, get_activity).

Shopify MCP server with real analytics (ShopifyQL), auto-refresh auth, and Shopify API 2026-04.

SkillDB io.github.devchad-cmd/skilldb

A registry of 5,900+ peer-authored skills any MCP agent can search and load on demand.

MCP gateway: bounded tool shortlists + artifact-backed result firewall. Deterministic, no model.

ArXiv io.github.guptaprakhariitr/arxiv-mcp

ArXiv preprint search, daily category digest, and author-collaborator graph.

AI security scanning and trust scoring. Stack-specific threat models. Free local scan.

EU AI Act + Colorado AI Act compliance scoring. 87/100 in 60 seconds. Free local scan.

Linux CVE prioritisation: 16 MCP tools for scan, fleet, runtime, and PR-able fix discovery.

lookup-disclose-io io.github.disclose/lookup-disclose-io

Find the right security-disclosure contact for any internet asset (domain, IP, package, repo, app).

Conta Azul MCP io.github.douglac/contaazul-mcp

Conta Azul ERP MCP — sales, customers, finance and NF-e via OAuth 2.0. Read + write, 35 tools.

Scan and generate barcodes and QR codes.

Scan Solana/Anchor code against the Solana Security Standard and serve the ruleset to MCP clients.

Predictive dependency security engine. Trust scores, zombie detection, blast radius analysis.

Website intelligence for AI agents: tech stack, hosting, security posture, SEO, and DNS.

Createya — AI Image & Video Generation io.github.Createya-ai/createya-mcp

100+ AI models: FLUX, Sora, Veo, Kling, Runway, Suno. OAuth or Bearer. No VPN. RU billing.

Dead code, security, secrets detection and code quality for Python, TypeScript, Go.

VaultCrux Memory Core io.github.CueCrux/vaultcrux-memory-core

VaultCrux Memory Core — 32 tools: knowledge, decisions, constraints, signals, coverage

Let AI agents interact with real BLE hardware — scan, connect, read, write, and subscribe.

AI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits for MCP agents.

hypernatt-terminal io.github.DIALLOUBE-RESEARCH/hypernatt-terminal

BTC/USDC decision context for AI agents from a live Hyperliquid vault; $0.001/call via x402.

Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.

value-us io.github.Densys/value-us

Verified deals, store policies & a trust score for thousands of online retailers. No auth.

Local-first security check for AI coding agents: secrets, .env exposure, git-history leaks, CVEs.

MCP server for t-rush. Exposes TODO/FIXME scanning and streak tracking to AI agents.