MCP 服务器大全
Model Context Protocol 服务器目录，覆盖协议版本、传输方式与能力清单。
收录口径
- 定义
- MCP server/client及能力、传输和权限资料。
- 收录边界
- 来源可追溯并标明能力声明性质。
- 不收录
- 不暗示安全审计或可用性保证。
MCP 服务器（18）
io.github.GuardBee/tool-poisoning-scanner
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
传输unknown厂商声明io.github.GuardBee/threat-rules
GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection
传输unknown厂商声明io.github.GuardBee/ssl-inspector
TLS certificate/cipher/protocol inspection
传输unknown厂商声明io.github.GuardBee/slopsquat-scanner
Checks declared npm/PyPI dependencies against real registries to catch slopsquatting
传输unknown厂商声明io.github.GuardBee/security-suite
Every GuardBee MCP security tool in one server: OWASP MCP Top 10, secrets, supply chain, TLS/DNS
传输unknown厂商声明io.github.GuardBee/security-proxy
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
传输unknown厂商声明io.github.GuardBee/security-engineer
Fix GuardBee AI Security Engineer findings in your repo with your coding agent, then verify
传输unknown厂商声明io.github.GuardBee/secret-scanner
Scans files for leaked secrets and API keys
传输unknown厂商声明io.github.GuardBee/rug-pull-detector
Baselines an MCP server's tools and detects tool-definition changes after approval
传输unknown厂商声明io.github.GuardBee/reverse-shield
Audits shipped apps for how easily they can be reverse engineered
传输unknown厂商声明io.github.GuardBee/prompt-leak-scanner
Catches leaked credentials and PII in outbound LLM prompts
传输unknown厂商声明io.github.GuardBee/prompt-injection-scanner
Scans RAG content/scraped pages for indirect prompt injection
传输unknown厂商声明io.github.GuardBee/owasp-scan
Unified OWASP MCP Top 10 scan — path or live tools/list, A–F grade, SARIF
传输unknown厂商声明io.github.GuardBee/oauth-auditor
Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience
传输unknown厂商声明io.github.GuardBee/model-scanner
Scans ML model files (PyTorch, joblib, NumPy, GGUF, TensorFlow…) and HF repos for supply-chain risks
传输unknown厂商声明io.github.GuardBee/memory-poisoning-scanner
Scans agent code for untrusted input poisoning persistent cross-session memory
传输unknown厂商声明io.github.GuardBee/mcp-server-auditor
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
传输unknown厂商声明io.github.GuardBee/mcp-config-auditor
Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats
传输unknown厂商声明
常见问题
- 什么是 MCP 服务器？
- MCP（Model Context Protocol）是连接 AI 应用与外部数据源、工具的开放协议。本目录当前收录 30917 个 MCP 服务器条目，范围：MCP server/client及能力、传输和权限资料。。
- 收录一个 MCP 服务器意味着什么？
- 仅代表整理了其公开的协议版本、传输方式、能力清单与权限声明，不构成安全审计或官方背书。
- 如何了解某个服务器的权限？
- 每个条目列出认证方式与权限范围；未经声明的能力标注为未知，本站不代为推断。