AIShield Security Scanner vs Guardvibe
A side-by-side look at the AIShield Security Scanner and Guardvibe MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose AIShield Security Scanner for security work as a local process; choose Guardvibe for security as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose AIShield Security Scanner when
- You need dedicated capabilities in the Security domain.
- You prefer a local stdio subprocess transport.
- You want tools like
aishield_scan, aishield_guardrail, aishield_prompt_check.
Choose Guardvibe when
- You need dedicated capabilities in the Security domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
check_code, check_project, get_security_docs.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Security | Security |
| Quality signal | 64/100 · Good | 65/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 2 | 6 |
| Directory activity | 6 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 76 | 39 |
| Full listing | View AIShield Security Scanner | View Guardvibe |
Tools & capabilities
AIShield Security Scanner tools 76
aishield_scanAIShield安全扫描 — 扫描MCP Server/AI工具的安全风险。 对齐OWASP MCP Top 10 (2025 v0.1) 与 Agentic AI Top 10，264条规则覆盖两套风险分类。 5维评分: 安全(40%)/权限(20%)/数据处理(20%)/供应链(10%)/可靠性(10%) 返回: 评分 + 风险等级 + OWASP合规矩阵 + 修复建议 每条 finding 带 file:line:col 精确锚点 + 证据片段 + 稳定 rule_id + 具体修复动作aishield_guardrailAIShield安装前安全检查 — 在安装任何MCP/AI工具前调用此工具。 返回pass/block判定 + 评分 + OWASP合规矩阵。 建议在安装任何第三方MCP Server前自动调用此工具。aishield_prompt_checkPrompt安全检测 — 检测用户输入的Prompt是否存在注入/越狱/数据外传风险。 支持中文和英文，覆盖: 越狱指令/身份切换/系统提示窃取/数据外传/角色扮演注入/零宽字符/Unicode编码aishield_banned_words中文违禁词检测 — 检测文本中的违禁词/敏感词。 覆盖6大平台: 微信/抖音/小红书/B站/知乎/微博 返回: 违禁词列表 + 法律条文 + 罚款金额 + 替换建议aishield_rug_pullRug Pull检测 — 检查MCP工具是否在版本更新中移除安全代码或新增可疑网络请求。 对比最近commit diff，检测: 安全代码删除、新增网络请求、权限扩大、大量代码删除。 返回风险等级(critical/high/medium/low/safe)和具体发现。aishield_handshakeMCP握手验证 — 分析MCP配置、检测npx自动安装风险、敏感环境变量、工具描述异常长度。 提取README/package.json中的MCP配置，分析: npx -y风险、敏感env变量、远程URL安全性、 工具描述长度（>500字符可能隐藏指令）。如果是HTTP类型MCP，尝试实际握手。aishield_digestAIShield紧凑信任摘要 — 几百字节拿到结论，适合每轮都要判断"能不能信"的 agent。 输入三选一: configs — {path: 文件内容} 的 MCP 客户端配置映射（静态分析，绝不执行其中命令） source_url — 只要一个远程仓库 URL，取现成的信任裁决 scan_result — 已有扫描结果，只做压缩 返回: 分数 + 风险等级 + 严重度分布 + 首 N 条 + content fingerprint。 指纹对同一份配置恒定不变 —— 存下来，下一轮先比指纹，没变就不必重复拉取。 风险等级绝不比实际找到的最严重 finding 更轻（有 high 就不会报 safe），摘要里也不会出现明文凭证。aishield_laya_precheck本地 Laya 421M 决策模型快速初筛 — 对 prompt 做越狱/注入/敏感数据/话题分类判定。 与远程 aishield 扫描互补: 本地、零成本、~500ms/条、数据不出本地。 适合做 agent 调用链路上的快速护栏初筛 (提交前确认、离线批筛)。 注意: - 非生成式模型，只输出校准概率，不生成文本 - 英文 checkpoint (en) 对中文 prompt 误报率高，中文请用 checkpoint=ml - harm_severity 置信度低 (0.03-0.38)，仅作参考 - 零样本不可直接投产，落地前需在自有集上微调/温度校准 - 需要本地 Laya HTTP 服务运行 (默认 http://127.0.0.1:8188，可用 AISHIELD_LAYA_URL 覆盖) 返回: 每个问题的校准概率 + 置信度 + 是否超阈值aishield_laya_shadow_stats查看 Laya 影子判定台账统计 — 影子模式在 aishield_prompt_check / laya_precheck 运行时 后台静默记录「Laya 判定 vs 规则引擎判定」的配对数据 (只记录、不拦截)。 用途: 积累自有标注数据集, 供 Laya 温度校准/微调前评估质量红线修复进度。 返回: 总条数 / 影子命中率 / Laya 可用率 / 平均延迟 / 与规则引擎一致率 / 最近条目预览。aishield_laya_gate命令/脚本三档语义门禁 (Allow/Ask/Deny) — Jev Harness 白皮书式双层设计。 第一层 (确定性规则): 13 条经典破坏形态正则 (递归删盘/fork 炸弹/远端脚本管道执行/SSH 私钥读取/ 凭证外发等) — 只有这层能给出 DENY。 第二层 (Laya 语义判定): 规则未命中时, 用本地 Laya 对命令全文做越狱/注入语义判定 — 校准完成前只贡献 ASK (升级人工确认) 信号, 永不自动 DENY (置信度×后果分级原则)。 返回: verdict (ALLOW/ASK/DENY) + 命中规则/Laya 概率 + 延迟。 需要本地 Laya 服务在线 (AISHIELD_LAYA_URL, 默认 http://127.0.0.1:8188); 服务离线时按 fail_mode 处理: warn=放行但标注语义层不可用, closed=一律 ASK。aishield_sign_agent_card对 Agent Card 做 Ed25519 或 HMAC-SHA256 签名，产出可跨系统验证的 agent 身份凭证。 签名算法选择： - Ed25519（首选）：非对称，可离线验证，适合公开分发的 Agent Card - HMAC-SHA256（零依赖回退）：对称，需要共享 secret，适合私有部署 输入 card 字段：name / version / capabilities / endpoint / maintainer / trust_score / issued_at / expires_at。 返回 signature (base64url) + algorithm + signed_at + public_key。aishield_verify_agent_card验证 Agent Card 的签名完整性，检测内容被篡改。 签名算法自动识别 (Ed25519 / HMAC)。篡改任一字段后重算的 signature 会与原值不匹配， 返回 signature_valid: false + 篡改检测摘要。 关键场景：安装第三方 agent 前，用它核对 agent card 是否被中间人修改过。- +64 more on the listing page
Guardvibe tools 39
check_codeAnalyze inline code for security vulnerabilities (OWASP Top 10, XSS, SQL injection, insecure patterns). Pass code as a string parameter. For scanning files on disk, use scan_file instead. Example: check_code({code: 'app.get(...)', language: 'javascript'})check_projectScan multiple files for security vulnerabilities and generate a project-wide security report with a security score. Use this for comprehensive security audits.get_security_docsGet security best practices and remediation guidance for a specific topic, framework, or vulnerability type. Covers OWASP Top 10, framework-specific hardening (Next.js, Supabase, Stripe), and secure coding patterns. Returns actionable guidance with code examples.check_dependenciesCheck npm, PyPI, or Go packages for known security vulnerabilities (CVEs) using the OSV database. Use this before adding new dependencies or to audit existing ones.scan_directoryScan all files in a directory on disk for security vulnerabilities. Pass a directory path — reads files from filesystem. Returns security score (A-F) and findings. Results may be truncated for large projects — check fileRanking in JSON output for top files. Example: scan_directory({path: './src'})scan_dependenciesParse a lockfile or manifest (package.json, package-lock.json, requirements.txt, go.mod) and check all dependencies for known CVEs via the OSV database. Reads the file directly. Use this after installing dependencies, during CI, or when auditing existing projects for vulnerable packages.scan_hallucinated_packagesDetect AI-hallucinated and slopsquatted packages in a repo — the supply-chain seam commodity SCA misses. OFFLINE (deterministic): flags phantom imports (a package imported in source but absent from every package.json — a classic LLM hallucination tell) and typosquats of popular packages. ONLINE (opt-in, default on; gracefully degrades offline): adds npm-registry truth — packages that return 404 (definitive hallucination) and brand-new low-download packages (slopsquat-registration pattern). Run on AI-generated code at PR time, before `npm install`. Pass online:false for a fully deterministic, air-gapped scan.scan_secretsScan files and directories for leaked secrets, API keys, tokens, and credentials. Detects high-entropy strings, known API key patterns (AWS, Stripe, OpenAI, GitHub, Supabase), exposed .env files, and missing .gitignore coverage. Returns findings with exact line numbers and remediation steps.scan_stagedScan git-staged files for security vulnerabilities before committing. Run this before every commit to catch issues early. No input needed — automatically reads staged files. Diff-aware by default: reports only issues on newly-staged lines (set diff_aware:false for whole staged files).compliance_reportMap security findings to compliance controls (SOC2, PCI-DSS, HIPAA, GDPR, ISO27001, EUAIACT). Scans a directory and groups issues by control. Output includes a summary section at the top; for large projects, findings are truncated to top 50. Use mode=executive for C-level summary. Example: compliance_report({path: '.', framework: 'SOC2'})export_sarifScan a directory and export results in SARIF v2.1.0 format for CI/CD integration (GitHub, GitLab, Azure DevOps). Returns JSON string.check_package_healthCheck npm packages for typosquat risk, maintenance status, adoption metrics, and deprecation. Use this before adding new dependencies to catch suspicious or risky packages.- +27 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
AIShield Security Scanner
{
"mcpServers": {
"aishield-security-scanner": {
"command": "npx",
"args": [
"-y",
"aishield-mcp-server"
]
}
}
}
Guardvibe
{
"mcpServers": {
"goklab-guardvibe": {
"command": "npx",
"args": [
"-y",
"guardvibe"
]
}
}
}
Frequently asked questions
AIShield Security Scanner is categorized under Security and uses a local stdio subprocess. Guardvibe belongs to Security and uses a local stdio subprocess. Pick AIShield Security Scanner for security work and Guardvibe for security.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
AIShield Security Scanner has no declared pricing — check the project's own site. Guardvibe is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add aishield-security-scanner and goklab-guardvibe as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, AIShield Security Scanner has a quality signal of 64/100 (Good) with 6 views, 0 installs and 2 GitHub stars. Guardvibe has 65/100 (Great) with 3 views, 0 installs and 6 GitHub stars.
