OWASP ZAP MCP Server

io.github.pierre3由 GitHub 账号 pierre3 发布v1.1.0更新于 Oct 25, 2026

MCP server for OWASP ZAP vulnerability scanning with Docker management

概览

AI 生成的概览

让 AI 助手驱动 OWASP ZAP 漏洞扫描的 MCP 服务器,支持爬虫、主动扫描、告警与报告,并内置 Docker 管理

可以做什么
通过 Docker Compose 工具启动、停止 ZAP 容器,查看状态和日志,或用 URL 与 API 密钥连接已有 ZAP 实例。使用标准爬虫和 Ajax 爬虫抓取目标,可指定已登录用户,并监控扫描进度。运行主动与被动扫描,并可随时停止。按风险等级分页读取告警,生成 HTML、JSON 或 XML 报告。管理上下文、认证方式、用户、凭据和强制用户模式,以支持认证扫描。
适用场景
适合让助手对你有权测试的网站执行 Web 安全扫描,从快速被动检查到带报告的认证主动扫描。适合已在使用 OWASP ZAP、希望从聊天客户端驱动扫描流程的开发者和测试人员。
运行要求
以 .NET 工具在本地运行,需要 .NET 10 SDK。内置 ZAP 容器管理需要支持 docker compose 的 Docker;否则需通过 ZAP_BASE_URL 和 ZAP_API_KEY 环境变量指向已有 ZAP 实例。通过工具启动容器时会自动生成 API 密钥。
安装前请注意
主动扫描会向目标发送真实攻击流量,只应扫描你拥有或获得书面许可的系统。服务器可启动和删除 Docker 容器,也可删除上下文和用户。认证扫描需通过凭据工具保存目标用户名和密码,ZAP API 密钥属于机密。README 含故意存在漏洞的示例应用,请勿对外暴露。

安装

在 SourceWeft 中

  1. 打开 控制台中的 OWASP ZAP MCP Server,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

dotnet-zap-mcp

[NuGet] [NuGet Downloads] [Release]

MCP (Model Context Protocol) server for OWASP ZAP. Enables AI agents (Claude, GitHub Copilot, etc.) to drive ZAP vulnerability scanning via MCP.

Features

  • 45 MCP tools for controlling OWASP ZAP (scanning, alerts, spider, ajax spider, context, authentication, reports, etc.)
  • Built-in Docker Compose management (start/stop ZAP with a single tool call)
  • Zero-config setup: auto-generates API keys and extracts Docker assets
  • Works with any MCP-compatible client (Claude Desktop, VS Code, etc.)

Installation

bash
dotnet tool install -g dotnet-zap-mcp

Prerequisites

  • .NET 10 SDK
  • Docker (Docker Engine or Docker Desktop) with docker compose support (for built-in ZAP container management)

Configuration

Zero-config (recommended)

No configuration needed. The agent calls DockerComposeUp which automatically:

  1. Extracts Docker assets to ~/.zap-mcp/docker/
  2. Generates a random API key
  3. Starts the ZAP container on localhost:8090
  4. Waits for ZAP to become healthy
Data persistence

The ZAP container uses two Docker named volumes:

VolumeContainer PathPurpose
zap-home/home/zap/.ZAPZAP settings, contexts, sessions, scan policies (persisted across restarts)
zap-data/zap/wrk/dataShared directory for reports, session files, and context import/export

On the first launch, the template config.xml is copied into zap-home. On subsequent launches, only the API key is updated — any changes made through ZAP (contexts, authentication settings, scan policies, etc.) are preserved.

The zap-data volume contains:

  • reports/ — generated scan reports
  • sessions/ — saved ZAP sessions
  • contexts/ — exported context files

Claude Desktop / Claude Code

Add to your MCP configuration:

json
{  "mcpServers": {    "zap": {      "command": "zap-mcp"    }  }}

VS Code (Copilot)

Add to .vscode/mcp.json:

json
{  "servers": {    "zap": {      "command": "zap-mcp"    }  }}

With existing ZAP instance

If you already have a ZAP instance running, pass connection details via environment variables:

json
{  "mcpServers": {    "zap": {      "command": "zap-mcp",      "env": {        "ZAP_BASE_URL": "http://localhost:8090",        "ZAP_API_KEY": "your-api-key"      }    }  }}

Available Tools

Docker Management

ToolParametersDescription
DockerComposeUp—Start the ZAP container and wait for healthy
DockerComposeDown—Stop and remove the ZAP container
DockerComposeStatus—Check container status
DockerComposeLogstailGet recent container logs

ZAP Core

ToolParametersDescription
GetVersion—Verify ZAP connectivity
GetHosts—List recorded hosts
GetSites—List recorded sites
GetUrlsbaseUrlList recorded URLs for a base URL

Spider

ToolParametersDescription
StartSpiderurl, maxChildren, recurse, subtreeOnly, contextNameStart a spider scan to crawl and discover pages
GetSpiderStatusscanIdCheck spider progress (0-100%)
GetSpiderResultsscanIdGet URLs discovered by spider
StopSpiderscanIdStop a running spider scan

Active Scan

ToolParametersDescription
StartActiveScanurl, recurse, inScopeOnly, scanPolicyName, contextIdStart an active vulnerability scan
GetActiveScanStatusscanIdCheck active scan progress (0-100%)
StopActiveScanscanIdStop a running active scan

Passive Scan

ToolParametersDescription
GetPassiveScanStatus—Check passive scan progress (records remaining)

Alerts

ToolParametersDescription
GetAlertsSummarybaseUrlAlert counts by risk level
GetAlertsbaseUrl, start, count, riskIdDetailed alert list with pagination and risk filter

Reports

ToolParametersDescription
GetHtmlReport—Generate HTML scan report
GetJsonReport—Generate JSON scan report
GetXmlReport—Generate XML scan report

Context Management

ToolParametersDescription
GetContextList—List all contexts defined in ZAP
GetContextcontextNameGet context details (scope patterns, etc.)
CreateContextcontextNameCreate a new context
RemoveContextcontextNameDelete a context
IncludeInContextcontextName, regexAdd URL include pattern to context scope
ExcludeFromContextcontextName, regexAdd URL exclude pattern to context scope
ImportContextcontextFilePathImport a context file into ZAP
ExportContextcontextName, contextFilePathExport a context to file

Authentication

ToolParametersDescription
GetAuthenticationMethodcontextIdGet the authentication method configured for a context
SetAuthenticationMethodcontextId, authMethodName, authMethodConfigParamsSet authentication method (form-based, JSON-based, script-based, HTTP)
SetLoggedInIndicatorcontextId, loggedInIndicatorRegexSet regex pattern indicating logged-in state
SetLoggedOutIndicatorcontextId, loggedOutIndicatorRegexSet regex pattern indicating logged-out state

Users

ToolParametersDescription
GetUsersListcontextIdList all users for a context
CreateUsercontextId, nameCreate a new user
RemoveUsercontextId, userIdRemove a user
SetAuthenticationCredentialscontextId, userId, authCredentialsConfigParamsSet user credentials (username/password)
SetUserEnabledcontextId, userId, enabledEnable or disable a user

Forced User

ToolParametersDescription
SetForcedUsercontextId, userIdSet the forced user for a context
SetForcedUserModeEnabledenabledEnable or disable forced user mode globally
GetForcedUserStatuscontextIdGet forced user mode status and current forced user

Ajax Spider

ToolParametersDescription
StartAjaxSpiderurl, inScope, contextName, subtreeOnlyStart the Ajax Spider for JavaScript-heavy apps
StartAjaxSpiderAsUsercontextName, userId, url, subtreeOnlyStart the Ajax Spider as a specific user
GetAjaxSpiderStatus—Get Ajax Spider status (running/stopped)
GetAjaxSpiderResults—Get Ajax Spider results summary
StopAjaxSpider—Stop the Ajax Spider

Typical Workflow

  1. Agent calls DockerComposeUp to start ZAP
  2. Configure browser/Playwright to use ZAP as proxy (http://127.0.0.1:8090)
  3. Browse the target application through the proxy
  4. Agent calls StartSpider to crawl the application, then GetSpiderStatus to monitor progress
  5. Agent calls GetPassiveScanStatus to wait for passive scan completion
  6. Agent calls StartActiveScan on key pages, then GetActiveScanStatus to monitor progress
  7. Agent calls GetAlertsSummary and GetAlerts to retrieve vulnerability findings
  8. Agent calls GetHtmlReport or GetJsonReport to generate a scan report
  9. Agent calls DockerComposeDown when done

Note: ZAP settings (contexts, authentication, scan policies) are persisted in the zap-home Docker volume. You can stop and restart the container without losing configuration.

Try It Out (with the included vulnerable app)

This repository includes an intentionally vulnerable web application for trying out ZAP scanning. The app contains common vulnerabilities (XSS, SQL Injection, CSRF, Open Redirect) so ZAP can detect real findings.

Setup

bash
# Start ZAP and the vulnerable target appdocker compose -f tests/docker/docker-compose.test.yml up -d --build
# Wait until both containers are healthydocker compose -f tests/docker/docker-compose.test.yml ps

Then configure your MCP client to connect to this ZAP instance:

json
{  "mcpServers": {    "zap": {      "command": "zap-mcp",      "env": {        "ZAP_BASE_URL": "http://localhost:8090",        "ZAP_API_KEY": "test-api-key-for-ci"      }    }  }}

The vulnerable app is accessible at http://target from within the Docker network (used by ZAP), and at http://localhost:8080 from your host machine.

Example 1: Quick Scan

Prompt to agent:

Scan http://target for vulnerabilities. Run a spider crawl, wait for the passive scan to finish, then show me the alert summary and generate an HTML report.

Expected tool flow:

GetVersion          → Verify ZAP connectivityStartSpider         → url: "http://target"GetSpiderStatus     → Poll until 100%GetPassiveScanStatus → Poll until 0 records remainingGetAlertsSummary    → baseUrl: "http://target"GetAlerts           → baseUrl: "http://target"GetHtmlReport       → Generate report

ZAP will discover pages like /search, /login, /users, /about, /contact, and the passive scan will report issues such as missing security headers and CSRF vulnerabilities.

Example 2: Authenticated Scan

The /admin page requires login (username: admin, password: password). An authenticated scan lets ZAP access protected pages.

Prompt to agent:

Set up an authenticated scan for http://target. The login form is at /login with fields "username" and "password" (credentials: admin / password). The logged-in indicator is "Welcome, admin". After configuring authentication, spider the site as the authenticated user and run an active scan.

Expected tool flow:

CreateContext                   → contextName: "target-auth"IncludeInContext                → regex: "http://target.*"SetAuthenticationMethod         → contextId, authMethodName: "formBasedAuthentication",                                  authMethodConfigParams: "loginUrl=http://target/login&loginRequestData=username%3D%7B%25username%25%7D%26password%3D%7B%25password%25%7D"SetLoggedInIndicator            → loggedInIndicatorRegex: "Welcome, admin"CreateUser                      → contextId, name: "admin"SetAuthenticationCredentials    → contextId, userId, authCredentialsConfigParams: "username=admin&password=password"SetUserEnabled                  → contextId, userId, enabled: trueSetForcedUser                   → contextId, userIdSetForcedUserModeEnabled        → enabled: trueStartSpider                     → url: "http://target", contextName: "target-auth"GetSpiderStatus                 → Poll until 100%GetPassiveScanStatus            → Poll until 0 records remainingStartActiveScan                 → url: "http://target"GetActiveScanStatus             → Poll until 100%GetAlertsSummary                → baseUrl: "http://target"GetAlerts                       → baseUrl: "http://target"SetForcedUserModeEnabled        → enabled: false

With authentication configured, ZAP can access /admin and test for vulnerabilities behind the login.

Example 3: Full Vulnerability Assessment

Prompt to agent:

Perform a full vulnerability assessment of http://target. Crawl the site, run an active scan, then give me a detailed breakdown of all discovered vulnerabilities grouped by risk level.

Expected tool flow:

StartSpider          → url: "http://target", recurse: trueGetSpiderStatus      → Poll until 100%GetSpiderResults     → Review discovered URLsGetPassiveScanStatus → Poll until 0 records remainingStartActiveScan      → url: "http://target", recurse: trueGetActiveScanStatus  → Poll until 100%GetAlertsSummary     → baseUrl: "http://target"GetAlerts            → baseUrl: "http://target", riskId: "3" (High)GetAlerts            → baseUrl: "http://target", riskId: "2" (Medium)GetAlerts            → baseUrl: "http://target", riskId: "1" (Low)GetHtmlReport        → Generate final report

The active scan will detect vulnerabilities including:

  • High: SQL Injection (/users?id=), Cross Site Scripting (/search?q=)
  • Medium: CSRF (missing tokens on /login), Open Redirect (/redirect?url=)
  • Low/Informational: Missing security headers, cookie issues, etc.

Cleanup

bash
docker compose -f tests/docker/docker-compose.test.yml down -v

License

MIT

来源:README.md,提交 e9c2b67

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.1.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分