经 AI Skill Hub 精选评估,Contrast安全MCP服务器 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.2 分,适合有一定技术背景的用户使用。
基于Java的MCP服务器实现,集成Contrast Security应用安全平台,提供代码安全扫描、漏洞检测和合规性验证能力。适合需要在AI应用中集成应用安全防护的开发团队和安全工程师。
Contrast安全MCP服务器 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
基于Java的MCP服务器实现,集成Contrast Security应用安全平台,提供代码安全扫描、漏洞检测和合规性验证能力。适合需要在AI应用中集成应用安全防护的开发团队和安全工程师。
Contrast安全MCP服务器 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/Contrast-Security-OSS/mcp-contrast
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"contrast--mcp---": {
"command": "npx",
"args": ["-y", "mcp-contrast"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 Contrast安全MCP服务器 执行以下任务... Claude: [自动调用 Contrast安全MCP服务器 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"contrast__mcp___": {
"command": "npx",
"args": ["-y", "mcp-contrast"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
The Contrast MCP Server allows you to connect Contrast Security to your AI coding agent to automatically remediate vulnerabilities, update insecure libraries, and analyze security coverage—all through natural language prompts.
[!WARNING] CRITICAL SECURITY WARNING: Exposing Contrast vulnerability data to an AI service that trains on your prompts can leak sensitive information. Only use mcp-contrast with environments that contractually guarantee data isolation and prohibit model training on your inputs. Verify AI Data Privacy: Confirm that your service agreement prevents model training on your prompts and consult your security team before sharing Contrast data. UNSAFE: Public consumer LLM sites (e.g., free ChatGPT, Gemini, Claude) that use prompts for training. POTENTIALLY SAFE: Enterprise services with contractual privacy guarantees (e.g., Google Cloud AI, AWS Bedrock, Azure OpenAI).
See CHANGELOG.md for the complete release history, including breaking changes and new features.
| Tool | Description |
|---|---|
search_vulnerabilities | Search vulnerabilities across all applications (org-level) |
search_app_vulnerabilities | Search vulnerabilities within a specific application with session filtering |
get_vulnerability | Get detailed vulnerability info including stack trace and remediation guidance |
list_vulnerability_types | List all available vulnerability types for filtering |
Alternatively, you can build from source if you need the latest development version. Requires Java 21+:
./gradlew :contrast-mcp-stdio-app:bootJar
The built JAR will be located at contrast-mcp-stdio-app/build/libs/mcp-contrast-X.X.X-SNAPSHOT.jar
Choose ONE of the following based on how you're running the JAR:
Use this if you're running the JAR directly from the command line or a script.
Add these two system properties to your java command:
-Dhttp_proxy_host=proxy.example.com
-Dhttp_proxy_port=8080
Complete example:
java \
-Dhttp_proxy_host=proxy.example.com \
-Dhttp_proxy_port=8080 \
-jar /path/to/mcp-contrast-X.X.X.jar \
--CONTRAST_HOST_NAME=example.contrastsecurity.com \
--CONTRAST_API_KEY=example \
--CONTRAST_SERVICE_KEY=example \
--CONTRAST_USERNAME=example@example.com \
--CONTRAST_ORG_ID=example
Use this if you're running the JAR through an MCP host (IntelliJ, Claude Desktop, Cline, etc.).
Add these two lines to the beginning of your args array:
"-Dhttp_proxy_host=proxy.example.com",
"-Dhttp_proxy_port=8080",
Complete example using IntelliJ's mcp.json:
{
"servers": {
"contrast": {
"command": "java",
"args": [
"-Dhttp_proxy_host=proxy.example.com",
"-Dhttp_proxy_port=8080",
"-jar",
"/path/to/mcp-contrast-X.X.X.jar",
"--CONTRAST_HOST_NAME=example.contrastsecurity.com",
"--CONTRAST_API_KEY=example",
"--CONTRAST_SERVICE_KEY=example",
"--CONTRAST_USERNAME=example@example.com",
"--CONTRAST_ORG_ID=example"
]
}
}
}
Choose ONE of the following based on how you're running Docker:
Use this if you're running Docker directly from the command line.
Add these two environment variables to your docker run command:
-e http_proxy_host="proxy.example.com" \
-e http_proxy_port="8080" \
Complete example:
docker run \
-e http_proxy_host="proxy.example.com" \
-e http_proxy_port="8080" \
-e CONTRAST_HOST_NAME=example.contrastsecurity.com \
-e CONTRAST_API_KEY=example \
-e CONTRAST_SERVICE_KEY=example \
-e CONTRAST_USERNAME=example \
-e CONTRAST_ORG_ID=example \
-i --rm \
contrast/mcp-contrast:latest \
-t stdio
Use this if you're running Docker through an MCP host (IntelliJ, VS Code, Claude Desktop, Cline, etc.).
Add these proxy settings:
Add to the args array (after the Contrast credentials):
"-e", "http_proxy_host",
"-e", "http_proxy_port",
Add to the env object:
"http_proxy_host": "proxy.example.com",
"http_proxy_port": "8080"
Complete example using IntelliJ's mcp.json:
{
"servers": {
"contrast": {
"command": "docker",
"args": [
"run",
"-e", "CONTRAST_HOST_NAME",
"-e", "CONTRAST_API_KEY",
"-e", "CONTRAST_SERVICE_KEY",
"-e", "CONTRAST_USERNAME",
"-e", "CONTRAST_ORG_ID",
"-e", "http_proxy_host",
"-e", "http_proxy_port",
"-i", "--rm",
"contrast/mcp-contrast:latest",
"-t", "stdio"
],
"env": {
"CONTRAST_HOST_NAME": "example.contrastsecurity.com",
"CONTRAST_API_KEY": "example",
"CONTRAST_SERVICE_KEY": "example",
"CONTRAST_USERNAME": "example@example.com",
"CONTRAST_ORG_ID": "example",
"http_proxy_host": "proxy.example.com",
"http_proxy_port": "8080"
}
}
}
}
For VS Code with input variables, see the VS Code Installation Guide.
If you're behind a corporate firewall or proxy, you'll need to configure proxy settings for the MCP server to reach your Contrast instance. The configuration differs depending on whether you're using Docker or JAR deployment.
Click the button above to automatically install in VS Code. For manual setup, see VS Code (GitHub Copilot) Installation Guide.
与Contrast Security深度集成的MCP实现,填补AI工具安全能力空白。项目成熟度有限(19星),建议关注更新频率和社区反馈。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:Contrast安全MCP服务器 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | mcp-contrast |
| 原始描述 | 开源MCP工具:MCP Server for Contrast Security。⭐19 · Java |
| Topics | 安全防护MCP服务应用安全漏洞检测Java |
| GitHub | https://github.com/Contrast-Security-OSS/mcp-contrast |
| License | Apache-2.0 |
| 语言 | Java |
收录时间:2026-05-21 · 更新时间:2026-05-22 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端