MCP Servers
Model Context Protocol servers
MCP (Model Context Protocol) servers are the newest surface we track — roughly 19,000 registries and repositories — and the highest-consequence one: an MCP server is a set of tools you deliberately hand to an AI agent that can read your files, call your APIs, and spend your tokens. The Shai-Hulud npm worm explicitly targeted Claude Code and MCP configuration files, which is the pattern to worry about here. We score MCP servers on tool permissions, transport security, credential handling, and the packages they pull in at runtime.
Tracked campaigns: Shai-Hulud
- Tool descriptions that instruct the agent to read ~/.ssh, .env, or browser credential stores
- Servers that install or execute packages at runtime
- Credential harvesting aimed at agent configuration files, as in Shai-Hulud
Security intelligence powered by Risky Plugins
19.8K
Extensions
19.8K
Analyzed
Risk Distribution
CRITICAL
130
HIGH
532
MEDIUM
4.5K
LOW
2.9K
MINIMAL
11.7K
Highest Risk Extensions
@kya-os/create-mcpi-app
h0bb5
655 findings 100
shadow-claw
GitHub Actions
9014 findings 100
foundersignal-mcp
carlosalvite
4083 findings 100
plumery-mcp
lapusta
422 findings 100
@evertrust/horizon-mcp
GitHub Actions
2922 findings 100
@skillsmith/mcp-server
GitHub Actions
74 findings 100
blun-king-cli
blunking
4079 findings 100
aismemory
GitHub Actions
628 findings 100
openregister-mcp
GitHub Actions
199 findings 100
@tokst/mcp-server
toskt
105 findings 100
Recently Analyzed
Other Marketplaces
Chrome Web Store
Google Chrome browser extensions
Firefox Add-ons
Mozilla Firefox browser extensions
VS Code Marketplace
Visual Studio Code extensions
Open VSX Registry
Open-source VS Code extensions
Notepad++ Plugins
Notepad++ editor plugins
Edge Add-ons
Microsoft Edge browser extensions
JetBrains Marketplace
JetBrains IDE plugins
n8n Community
n8n workflow automation nodes
AI Agent Skills
Agent skills for Claude Code, Codex CLI and Gemini CLI