DefectDojo MCP Server
DefectDojo MCP 服务器
该项目为流行的开源漏洞管理工具DefectDojo提供了一个模型上下文协议 (MCP)服务器实现。它允许 AI 代理和其他 MCP 客户端以编程方式与 DefectDojo API 进行交互。
特征
该 MCP 服务器公开了用于管理关键 DefectDojo 实体的工具:
**发现:**获取、搜索、创建、更新状态和添加注释。
**产品:**列出可用的产品。
**约定:**列出、检索详细信息、创建、更新和结束约定。
Related MCP server: Agent Construct
安装与运行
有几种方法可以运行此服务器:
使用uvx (推荐)
uvx在临时虚拟环境中执行 Python 应用程序,自动安装依赖项。
uvx defectdojo-mcp使用pip
您可以使用pip将包安装到您的 Python 环境中。
# Install directly from the cloned source code directory
pip install .
# Or, if the package is published on PyPI
pip install defectdojo-mcp通过 pip 安装后,使用以下命令运行服务器:
defectdojo-mcp配置
服务器需要以下环境变量来连接到您的 DefectDojo 实例:
DEFECTDOJO_API_TOKEN(必需):用于身份验证的 DefectDojo API 令牌。DEFECTDOJO_API_BASE(必需):您的 DefectDojo 实例的基本 URL(例如,https://your-defectdojo-instance.com)。
您可以在 MCP 客户端的设置文件中配置这些。以下是使用uvx命令的示例:
{
"mcpServers": {
"defectdojo": {
"command": "uvx",
"args": ["defectdojo-mcp"],
"env": {
"DEFECTDOJO_API_TOKEN": "YOUR_API_TOKEN_HERE",
"DEFECTDOJO_API_BASE": "https://your-defectdojo-instance.com"
}
}
}
}如果您使用pip安装该软件包,则配置将如下所示:
{
"mcpServers": {
"defectdojo": {
"command": "defectdojo-mcp",
"args": [],
"env": {
"DEFECTDOJO_API_TOKEN": "YOUR_API_TOKEN_HERE",
"DEFECTDOJO_API_BASE": "https://your-defectdojo-instance.com"
}
}
}
}可用工具
可通过 MCP 界面使用以下工具:
get_findings:通过过滤(产品名称、状态、严重性)和分页(限制、偏移)检索结果。search_findings:使用文本查询搜索结果,并进行过滤和分页。update_finding_status:更改特定发现的状态(例如,活动、已验证、误报)。add_finding_note:为发现添加文本注释。create_finding:创建与测试相关的新发现。list_products:列出具有过滤(名称、产品类型)和分页功能的产品。list_engagements:列出带有过滤(product_id、status、name)和分页的参与度。get_engagement:通过 ID 获取特定参与的详细信息。create_engagement:为产品创建新的约定。update_engagement:修改现有约定的详细信息。close_engagement:将约定标记为已完成。
(每个工具的详细使用示例请见下方README原文内容)
使用示例
(注意:这些示例假设 MCP 客户端环境能够调用use_mcp_tool )
获取调查结果
# Get active, high-severity findings (limit 10)
result = await use_mcp_tool("defectdojo", "get_findings", {
"status": "Active",
"severity": "High",
"limit": 10
})搜索结果
# Search for findings containing 'SQL Injection'
result = await use_mcp_tool("defectdojo", "search_findings", {
"query": "SQL Injection"
})更新结果状态
# Mark finding 123 as Verified
result = await use_mcp_tool("defectdojo", "update_finding_status", {
"finding_id": 123,
"status": "Verified"
})为发现添加注释
result = await use_mcp_tool("defectdojo", "add_finding_note", {
"finding_id": 123,
"note": "Confirmed vulnerability on staging server."
})创建发现
result = await use_mcp_tool("defectdojo", "create_finding", {
"title": "Reflected XSS in Search Results",
"test_id": 55, # ID of the associated test
"severity": "Medium",
"description": "User input in search is not properly sanitized, leading to XSS.",
"cwe": 79
})列出产品
# List products containing 'Web App' in their name
result = await use_mcp_tool("defectdojo", "list_products", {
"name": "Web App",
"limit": 10
})列出参与活动
# List 'In Progress' engagements for product ID 42
result = await use_mcp_tool("defectdojo", "list_engagements", {
"product_id": 42,
"status": "In Progress"
})获得参与
result = await use_mcp_tool("defectdojo", "get_engagement", {
"engagement_id": 101
})创造参与度
result = await use_mcp_tool("defectdojo", "create_engagement", {
"product_id": 42,
"name": "Q2 Security Scan",
"target_start": "2025-04-01",
"target_end": "2025-04-15",
"status": "Not Started"
})更新参与度
result = await use_mcp_tool("defectdojo", "update_engagement", {
"engagement_id": 101,
"status": "In Progress",
"description": "Scan initiated."
})密切接触
result = await use_mcp_tool("defectdojo", "close_engagement", {
"engagement_id": 101
})发展
设置
克隆存储库。
建议使用虚拟环境:
python -m venv .venv source .venv/bin/activate # On Windows use `.venv\Scripts\activate`安装依赖项,包括开发依赖项:
pip install -e ".[dev]"
执照
该项目根据 MIT 许可证获得许可 - 有关详细信息,请参阅LICENSE文件。
贡献
欢迎贡献!欢迎随时提交问题,包括错误报告、功能请求或疑问。如果您想贡献代码,请先提交问题,讨论建议的更改。
Available Tools
11 toolsadd_finding_noteC
Add a note to a finding
Inputs: finding_id (required), note (required). Returns: result
close_engagementC
Close an engagement
Inputs: engagement_id (required). Returns: result
create_engagementD
Create a new engagement
Inputs: name (required), product_id (required), status (required), target_end (required), +10 more.
create_findingD
Create a new finding
Inputs: description (required), severity (required), test_id (required), title (required), +5 more. Returns: result
get_engagementB
Get a specific engagement by ID
Inputs: engagement_id (required). Returns: result
get_findingsC
Get findings with filtering options and pagination support
Inputs: limit, offset, product_name, severity, +1 more. Returns: result
list_engagementsC
List engagements with optional filtering and pagination support
Inputs: limit, name, offset, product_id, +1 more. Returns: result
list_productsC
List all products with optional filtering and pagination support
Inputs: limit, name, offset, prod_type. Returns: result
search_findingsC
Search for findings using a text query with pagination support
Inputs: query (required), limit, offset, product_name, +2 more. Returns: result
update_engagementC
Update an existing engagement
Inputs: engagement_id (required), branch_tag, build_id, commit_hash, +10 more. Returns: result
update_finding_statusB
Update the status of a finding (Active, Verified, False Positive, Mitigated, Inactive)
Inputs: finding_id (required), status (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Each tool has a clearly distinct purpose targeting specific resources and actions, such as create_engagement vs. update_engagement, and get_findings vs. search_findings, with no overlapping or ambiguous functions.
All tool names follow a consistent verb_noun pattern using snake_case, such as create_engagement, list_products, and update_finding_status, with no deviations in style or convention.
With 11 tools, the server is well-scoped for defect management, covering key operations like engagements, findings, and products without being overly sparse or bloated.
The tool set provides strong CRUD/lifecycle coverage for engagements and findings, including create, get, update, and list operations, though minor gaps like product creation or deletion might require workarounds.
Related MCP Connectors
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server for DefectDojo vulnerability management, exposing 24 tools for managing products, engagements, tests, findings, scan imports, and finding lifecycle through the Model Context Protocol.2431 PyPI1MIT
- AlicenseNot gradedqualityDmaintenanceModel Context Protocol server that standardizes tool discovery, execution, and context management for AI applications.MIT
- AlicenseNot gradedqualityDmaintenanceModel Context Protocol server that connects AI agents with CrowdStrike Falcon platform for intelligent security analysis and automation.MIT
- AlicenseCqualityBmaintenanceA Model Context Protocol (MCP) server that provides comprehensive access to DefectDojo vulnerability management platform.78MIT