MCP Customs
Inspect an MCP server for common security risks before you install it. Offline, zero telemetry.
ค้นด้วยงานที่อยากทำหรือชื่อโปรแกรม แล้วกรองตามหมวด
เรียงตามคะแนนการใช้งาน: ดาว GitHub ยอดดาวน์โหลดต่อสัปดาห์ ความสดของการออกรุ่น และ endpoint ที่ยังตอบ ใช้มากไม่ได้แปลว่าดีกว่า
อ่านการ์ด:↓ ดาวน์โหลดต่อสัปดาห์i★ ดาว GitHubiสามเสา: รีวิว · ผลตรวจ · การใช้งานiอัปเดต = วันที่ส่งรุ่นล่าสุดเข้า registryi
Inspect an MCP server for common security risks before you install it. Offline, zero telemetry.
Programmatic control of the Hiro security platform: scans, tasks, plans, and approvals.
Read-only discovery of Framekeep capabilities, security boundaries, and public resources.
Permission before writes. Gravity→DENYs→Session $0.25. Pilot $100; Gateway $299. Probe free.
Search 10k+ live cybersecurity jobs from 246 security companies, plus salary benchmarks and stats.
OSINT sweep of a digital footprint: breaches, accounts, data brokers, domains and IPs
Encrypted store for API keys and database URLs your code needs. Use them without reading them.
Browse Aevum Security's Singapore cybersecurity services and submit a business enquiry.
Local supply-chain CVE scanner via OSV/NVD. Scans deps and IDE extensions. No upload.
Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.
Mocap, rehab biomechanics, threat intel, fleet vision. 21 MCP tools, 10 free. x402/USDC paid.
Local MCP proxy: collapses N servers' tools into 4 meta-tools and compresses large tool outputs.
Query Truss threat intelligence via hosted MCP (OAuth). Growth+ plans.
Send end-to-end encrypted email and files. Encryption happens on your machine, not our server.
Query Microsoft Patch Tuesday security updates (MSRC) with EPSS and CISA KEV enrichment
Fail-closed action authorization, MCP risk scanning, x402 checks, and signed receipts.
Manage Proxmox VE via Cursor: QEMU, LXC, storage, HA, firewall, access.
Manage UniFi sites, devices, clients, networks, port forwarding, DNS, and firewall
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
Public MCP digital twin with synthetic systems and an agent firewall. No customer data.