探索 MCP Server 与 Agent Skill

io.github.devops-infinity/ownserp

MCP server for the Serper.dev search API with per-call credit accounting

io.github.niklas-schmidt-dev/mobdev

Mac app that lets AI agents drive iPhones, iOS simulators and Android: tap, type, install, logs.

io.github.jeremdecustovox/custovox-ticket-scorer

custovox.ai support ticket scoring MCP server: priority, category, sentiment, escalation risk

io.github.jeremdecustovox/custovox-emotion

custovox.ai MCP server: 7-emotion detection in English customer text (batch up to 50)

io.github.jeremdecustovox/custovox-sentiment

custovox.ai multilingual customer sentiment analysis MCP server (EN/FR/DE/ES/PT-BR)

io.github.jeremdecustovox/custovox-review-analyzer

custovox.ai MCP server: customer review sentiment breakdown and summaries (up to 100 reviews)

io.github.kznlabs/labsui

Search, add, diff and update labsUI React components in your project.

io.github.Robert0303-C/screenrec-agent

Record a real browser page and cut it into a publishable vertical video. Local, no cloud.

io.alterlab/mcp-server

网页抓取 MCP 服务器——抓取页面、提取结构化数据、对任意网站截图，支持反爬绕过。

com.agentbrokerindex/agentbroker-index

Read-only, sourced data on which brokers, banks and crypto exchanges AI agents can use (EU/Spain).

com.getaroundhongkong/trip-planner

Hong Kong public transport trips (MTR, bus, minibus, ferry), live times, fares and border queues.

com.tollylabs/x402-mcp

Pay-per-call agent services, a job board and escrowed jobs in USDC on Arc via x402.

io.github.GuardBee/threat-rules

GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection

io.github.GuardBee/slopsquat-scanner

Checks declared npm/PyPI dependencies against real registries to catch slopsquatting

io.github.GuardBee/prompt-leak-scanner

Catches leaked credentials and PII in outbound LLM prompts

io.github.GuardBee/context-oversharing-auditor

OWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks

io.github.GuardBee/toxic-flow-auditor

Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress

io.github.GuardBee/vector-store-scanner

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

io.github.GuardBee/unbounded-consumption-auditor

Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)

io.github.GuardBee/oauth-auditor

Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience

io.github.GuardBee/ssl-inspector

TLS certificate/cipher/protocol inspection

io.github.GuardBee/vulnerability-scanner

Triggers GuardBee scans, queries findings, AI-assisted remediation guidance