HackerOne MCP
Connects Claude to the HackerOne Hacker API, enabling program listing, scope retrieval, report management, and balance checks via natural language.
README
HackerOne MCP
An MCP server that connects Claude to the HackerOne Hacker API. List your programs, pull structured scope, read and submit reports, browse Hacktivity, and check your balance — all from inside Claude Code.
Tools
| Tool | What it does |
|---|---|
test_connection |
Verify credentials work (run this first) |
list_programs |
List programs you can access |
get_program |
Full details for one program by handle |
get_program_scope |
Structured scope (in-scope assets), filter by bounty/submission |
get_program_weaknesses |
Accepted weakness (CWE) types |
get_scope_exclusions |
Out-of-scope categories |
search_scope |
Search a keyword across ALL your programs' scopes |
list_my_reports |
Reports you've submitted |
get_report |
One report by ID (activities, bounties, state) |
submit_report |
Submit a new vulnerability report |
hacktivity |
Query publicly disclosed reports for intel |
get_balance / get_earnings / get_payouts |
Money |
hackerone_api |
Raw passthrough for any other endpoint |
Setup
1. Get an API token
Go to https://hackerone.com/settings/api_token/edit, create a token, and note both the identifier (username) and the token value.
2. Install deps
cd ~/projects/hackerone-mcp
uv venv .venv
uv pip install --python .venv/bin/python -r requirements.txt
3. Add credentials
cp .env.example .env
# edit .env and fill in HACKERONE_API_USERNAME + HACKERONE_API_TOKEN
The server auto-loads .env from this folder — nothing else to configure.
4. Test
.venv/bin/python -c "import hackerone_mcp as h; print(h.test_connection())"
5. Register with Claude Code
claude mcp add hackerone -- ~/projects/hackerone-mcp/.venv/bin/python ~/projects/hackerone-mcp/hackerone_mcp.py
Then in Claude: "list my HackerOne programs" or "pull the scope for program X".
To register only for the current project instead, add --scope project.
Manual config (any MCP client)
{
"mcpServers": {
"hackerone": {
"command": "/home/kali/projects/hackerone-mcp/.venv/bin/python",
"args": ["/home/kali/projects/hackerone-mcp/hackerone_mcp.py"]
}
}
}
Credentials come from .env, or set HACKERONE_API_USERNAME /
HACKERONE_API_TOKEN in the env block of the config.
Notes
- Base URL:
https://api.hackerone.com/v1, HTTP Basic auth. submit_reportcreates a real report — review details before calling..envis gitignored; never commit your token.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。