Search
@harper-concierge/seon-sdk
harper-developers
This module provides a TypeScript class, Seon, to interact with Seon's Fraud API. The Seon class allows you to send fraud detection requests using the provided API key and endpoint URL.
...more@pramodyadav027/dependency-health-mcp
pramodyadav027
MCP server for monitoring dependency health across projects
@roleplay-sh/cli
ibrahimcheurfa
Paid social-engineering workbench CLI for AI agents.
watchlight-claude-agent
Watchlight AI <[email protected]>
Governed Claude Agent SDK agents with Watchlight — authorize every agent action, fail-closed, with zero infrastructure. Independent plugin, not affiliated with Anthropic.
...moreblastradius-mcp
Harris Ahmad
Cross-repo infrastructure memory for coding agents
@console-agent/agent
agent5ive
Drop console.agent(...) anywhere in your code to execute agentic workflows — as easy as console.log()
@libp2p/crypto
npm-service-account-libp2p
Crypto primitives for libp2p
@gatewaystack/gatewaystack-governance
davidcrowe
GatewayStack governance layer for OpenClaw — identity, scope, rate limiting, injection detection, and audit logging for every tool call
...more@microsoft/agentmesh-copilot-governance
microsoft1es
Public Preview — GitHub Copilot Extension for agent governance code review: detects missing policy checks, unguarded tool calls, and audit logging gaps
...moremetorial/metorial
🎖️ 📇 ☁️ Connect AI agents to 600+ integrations with a single interface - OAuth, scaling, and monitoring included
pg-guard-mcp
Berkant Acun
A PostgreSQL MCP server that enforces read-only access at the protocol and privilege level — not by parsing the query string.
...moreimrobot
leo_pechnicki
I'm a robot. Reverse-CAPTCHA that verifies AI agents and robots, not humans.
Cti Expert
7onez
CTI Expert — Cyber Threat Intelligence & OSINT analysis skill for Claude Code / Codex. 120+ commands, 57 techniques, 79 typed MCP tools, deterministic case pipeline + ICD-203 reports. No API keys required for core.
...morep3x-network-mcp
patrikx3
🔍 P3X Network MCP: AI-powered network analysis MCP server
@mcpskillsio/server
riseabovepartners
Trust-score any AI skill or MCP server from inside Claude Code, Cursor, or any MCP client. 14 signals, safety scanning, recommendations, badges, and monitoring.
...morewhats-inherited-mcp
Zachary Pampu
MCP server that shows what a checkout you did not write tells your agent to do — instruction files, hook commands wired to agent events, MCP servers it declares, and the skills and subagents it ships.
...more@weiseer/mcp-doctor
weiseer
Install-time trust gate for MCP servers — PASS/WARN/BLOCK + cited evidence + GitHub Action support.
@huatalk/hiding-skill
GitHub Actions
Strategic content cleanup for files that should reveal less about their origin, process, AI participation, constraints, or sensitive context.
...moreskillcap-lock
dhait
Review what an Agent Skill can newly do, not just what bytes changed.
Avakill
log-bell
🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Anthropic, LangChain, and MCP. She doesn't guard. She kills.
...more