AiTest123.comAI 评测与可信度检测平台
拖动滑块完成拼图，通过后发送验证码
独立第三方 AI 评测平台 · 只用实测数据
挂「security」这个标签的服务器清单：逐条给出安装命令、连接方式、鉴权方式与仓库地址，可以先按分类与连接方式判断哪些适合你的环境，再进详情页看接入参数。
挂「security」标签的服务器共 103 个，以开发工具（40）、安全风控（27）、AI代理（14）为主。其中 42 个给出可直接使用的安装命令或远程端点，22 个用 stdio 在本地拉起进程、5 个连远程 HTTP 端点。
本地 stdio 与远程 HTTP 都有：本地数据选 stdio（数据不出本机），SaaS 类选 HTTP（不用装运行时）。
OAuth 授权可以随时撤销，相对安全；API Key 与 Token 是长期凭据，用只读或最小权限的那把。
golproductions · 安全风控
Anti-hallucination firewall for AI coding agents. Validates commands before execution, imports against your package.json, function calls against your source files. Sub-100ms. $0.0068 AUD per check, 120 free on sign-up.
npx -y @golproductions/check-mcp
支持 Claude Desktop、Claude、Cursor ai agents、security、preflight、devtools
Compuute · 开发工具
Scan-as-a-Service for MCP servers — HTTP+MCP wrapper around compuute-scan
pip install -r requirements.txt
支持 Claude、Cursor、Codex security、mcp、static analysis、vulnerability scanner
terno-ai · 数据服务
TernoDBI is a database intelligence layer designed for Security and Accuracy, bridging the gap between AI Agents and Enterprise Data. It acts as a powerful standalone Model Context Protocol (MCP) server, or it can be directly embedded into your existing Django projects. Either wa
uvx --from terno-dbi dbi-mcp query
支持 Claude Desktop、Claude、Cursor security
jerrywrongalot-byte · 开发工具
MCP server: AI agents share self-destructing one-time secrets via DeadDrop - zero-knowledge, paid per call in USDC over x402 on Base
上游未给出安装命令，详情页看接入方式
支持 Claude Desktop、Claude、Cursor x402、secrets、zero knowledge、usdc
node-man · 开发工具
Domain security reconnaissance for AI agents — 13 tools (DNS, SSL, HTTP headers, email auth, port scan, ASN, RDAP) with a 0–100 Health Score. Free, no API key
上游未给出安装命令，详情页看接入方式
支持 Claude、Cursor、VS Code security、dns、ssl、osint
dynamicfeed · 地图位置
Official stdio MCP server for Dynamic Feed — bridges any MCP client to 62 live, signed data tools at dynamicfeed.ai. Works through firewalls that block remote SSE.
npx -y dynamicfeed-mcp
支持 Claude Desktop、Claude、Cursor data、weather、australia、finance
romans-repos · 开发工具
Daily, Ed25519-signed security intelligence for AI-agent stacks: CVEs, supply-chain incidents and advisories (GHSA/CISA-KEV/OSV/NVD + national-CERT) assessed for MCP/LLM-proxy impact, cross-validated and signed. Paid via x402 ($0.10 USDC on Base); free sample, list_available, che
上游未给出安装命令，详情页看接入方式
支持 Claude、Cursor、Codex mcp、x402、security、cve
Agnuxo1 · AI代理
AES-256-GCM + Argon2id encrypted local vault for AI agent credentials. Store API keys, tokens, and passwords safely. Reference them as {{PLACEHOLDER}} in any AI workflow — LangChain, CrewAI, AutoGen, n8n, and 40+ frameworks.
npx esbuild argon2-entry.js \\
支持 Claude、Cursor、VS Code mcp、security、vault、credentials
entropy0dev · 安全风控
Source trust for AI agents — evaluates URLs and domains before ingestion, returns proceed/deny decisions with scores and reason codes.
pip install entropy0-langchain
支持 Claude Desktop、Claude、Cursor mcp、trust、security、ai agents
Armada735 · 开发工具
Audits a GitHub repository's stargazers for signs of fake-star injection across five deterministic axes (burst, suffix-farm, sequential-id cluster, same-second cluster, inter-star gap regularity) over two windows (oldest 100 + newest 30), plus extended signals. Returns LOW / MEDI
uvx fake-star-audit
支持 Claude Desktop、Claude、Cursor github、security、due diligence、osint
GateplexAI · 安全风控
Governance firewall for autonomous AI agents. Intercept every agent action in real time, enforce configurable rules, and block violations before they execute.
上游未给出安装命令，详情页看接入方式
支持 Cursor、Codex、Zed ai governance、mcp、ai agents、llm
78degrees · 开发工具
Find every leaked secret on your machine. Scans .env files, shell history, and config directories for API keys, tokens, and credentials. 35+ patterns including AWS, Stripe, GitHub, OpenAI, and more. Everything runs locally. Zero network calls.
npx -y ghosthunt
支持 Claude Desktop、Claude、Cursor security、secrets、mcp、api keys
GoPlusSecurity · 安全风控
GoPlus Security is the leading Web3 security layer, providing comprehensive protection for multiple blockchain ecosystems. This project provides a MCP server for LLM Client to connect to the GoPlus Security Intelligence. Through this server, LLM Client can directly access and ana
npx -y goplus-mcp@latest --key YOUR_GOPLUS_API_KEY --secret YOUR_GOPLUS_API_SECRET
支持 Claude Desktop、Claude、Cursor security、web3、mcp、token
fishcoco-code · 开发工具
Non-invasive AI Agent operation monitoring — audit every API call your agent makes to Shopify, Meta Ads, and more. Real-time alerts, audit logs, and operation history. Works with Claude Desktop, Cursor, and any MCP-compatible AI tool.
上游未给出安装命令，详情页看接入方式
支持 Claude Desktop、Claude、Cursor monitoring、security、shopify、meta ads
Br0ski777 · 开发工具
MCP server for generating cryptographic hashes (MD5, SHA-1, SHA-256, SHA-512, RIPEMD-160). Pay-per-use via x402 protocol (USDC on Base). Use this when you need to hash strings, verify data integrity, or generate checksums.
上游未给出安装命令，详情页看接入方式
支持 Cursor、Codex、Zed hash、crypto、security、x402
caglarbozkurt · 开发工具
Security scanner for MCP servers — vet an MCP before you wire it into an agent. Detects prompt-injection, credential exfiltration (via taint analysis), RCE, and supply-chain risks, and catches cross-server exfil chains no single server reveals. Zero-dependency local CLI, SARIF ou
npx -y --package mcp-heimdall-scan heimdall-mcp
支持 Claude Desktop、Claude、Cursor cli、security、mcp、compliance
shashwat-sec · 安全风控
Lacework Alerts MCP Server An MCP (Model Context Protocol) server built with FastMCP that exposes Lacework API v2 alert operations as tools for AI agents and LLM integrations. Quick Start (New Machine Setup) `bash 1. Clone the repo git clone <repo-url> cd lacework_mcp_server 2. Create a virtual environment (Python 3.10+) python3 -m venv .venv source .venv/bin/activate 3. Install d
/path/to/lacework_mcp_server/.venv/bin/python /path/to/lacework_mcp_server/lacework_mcp_…
支持 Claude Desktop、Claude、Cursor security、mcp、server
Amywith · AI代理
LLM-Guard 隐私网关 一个基于MCP协议的隐私保护网关，用于在LLM应用中检测和过滤敏感信息。 功能特性 1. PII脱敏：自动识别文本中的中文人名、手机号、邮箱，并将其替换为占位符 2. 密钥拦截：检测常见的API Key、阿里云AccessKey以及RSA私钥 3. 商业阻断：定义黑名单列表，如果文本包含这些词，直接返回拦截状态 4. MCP封装：将上述逻辑封装为MCP工具，返回JSON格式的处理结果 安装 `bash pip install -r requirements.txt ` 关于spaCy模型下载问题 如果您在下载spaCy中文语言模型时遇到网络问题（如连接被远程主机关闭），可以尝试以下解决方案： 解决方案1：使用国内镜像源 `bash pip install -i https://pyp
pip install -r requirements.txt
支持 Cursor、Codex、Zed security
Hustada · 开发工具
Store and retrieve API keys and secrets locally for Claude Code. No cloud services, no .env files scattered across projects. Secrets are stored in a SQLite database on your machine and accessed via MCP tools. Supports add, get, list, search, update, and delete operations with cat
上游未给出安装命令，详情页看接入方式
支持 Claude、Cursor、VS Code secrets、api keys、claude code、security
srmadscience · 数据服务
Oracle MCP server with no run-sql tool: It generates tools for each of the PL/SQL procedures, tables and approved SQL you choose. The server doesn't expose a SQL prompt, and can't reveal how it's connected to Oracle.
上游未给出安装命令，详情页看接入方式
支持 Claude、Cursor、Codex oracle、oracle database、database、security
kapilduraphe · 安全风控
A comprehensive security scanner for Model Context Protocol (MCP) servers that detects vulnerabilities and security issues in your MCP implementations.
上游未给出安装命令，详情页看接入方式
支持 Cursor、Codex、Zed mcp、security、scanner
mandatez · 金融服务
MandateZ Every agent needs a mandate. MandateZ is the neutral trust infrastructure layer for AI agents. Cryptographic identity, policy enforcement, human oversight gates, and tamper-proof audit trails — for every agent, across every framework. Why MandateZ AI agents are autonomous. They read files, call APIs, send emails, make payments. Nobody can prove what they did, whether they were au
上游未给出安装命令，详情页看接入方式
支持 Cursor、Codex、Zed security、ai agents、audit trail、trust
marchward · AI代理
Marchward is an Apache-2.0 open-source runtime authority for AI agents. It routes an agent's tool calls through one control point: credential mediation (the agent holds a single Marchward key and never your real downstream credentials), an inference spend cap enforced before the
上游未给出安装命令，详情页看接入方式
支持 Claude、Cursor、Gemini CLI ai agents、agent governance、mcp、security
faizbawa · 开发工具
MCP server giving AI agents full SSH access with secret-safe environment variable injection. Supports persistent sessions, structured command execution, SFTP file transfer, port forwarding, and automatic output redaction that prevents secrets from reaching the LLM.
上游未给出安装命令，详情页看接入方式
支持 Claude、Cursor、VS Code ssh、remote access、devops、secrets
共 103 个服务器被上游打了「security」这个标签，覆盖最多的是 开发工具（40）、安全风控（27）、AI代理（14）、金融服务（9）。其中 22 个用 stdio 在本地拉起进程，5 个连远程 HTTP 端点，42 个给出了可直接使用的安装命令或端点地址。
点开任意一条进详情页：安装命令是本地命令的，复制后执行并重启客户端；安装命令是一串 http(s) 地址的，说明它是远程端点，把地址填进客户端的 MCP 配置即可，不用在本地装运行时。接入前先看一眼鉴权方式——API Key、Token 是长期凭据，建议用只读或最小权限的那把。
分类页是上游给的 15 个大类，一个类下什么用途都有；标签专题按服务器实际带的关键词归类，「security」就是其中一类，粒度更细、也允许一台服务器同时出现在多个标签下。想按大类浏览回 MCP 服务器大全（/mcp），想换一个标签回标签专题总入口（/mcp/topic）。
服务器信息以作者仓库与官方文档为准；标签、分类与连接方式的中文说明为中文整理，数据日期 2026-10-11 21:56:06。
