HackerOne MCP Server
Enables MCP clients like Claude and Codex to interact with HackerOne's API to list and get reports, programs, and scopes.
README
HackerOne MCP Server
An MCP (Model Context Protocol) server that connects Claude, Codex, and other MCP clients to the HackerOne Hackers API.
Tools Available
| Tool | Description |
|---|---|
h1_list_reports |
List your reports, filterable by program, state, severity, page |
h1_get_report |
Get full details of a specific report by ID |
h1_get_program_scopes |
Get in-scope and out-of-scope assets for a program |
h1_get_program |
Get program details (policy, bounties, response stats) |
h1_list_programs |
List programs you have access to |
Setup
1. Install dependencies
cd hackerone-mcp
npm install
2. Get your HackerOne API credentials
- Go to https://hackerone.com/settings/api_token/edit
- Create a new API token
- Note your username and the generated token
Configuration
Claude Desktop
Edit your Claude Desktop config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"hackerone": {
"command": "node",
"args": ["/absolute/path/to/hackerone-mcp/index.js"],
"env": {
"HACKERONE_API_USERNAME": "your_api_token_identifier",
"HACKERONE_API_TOKEN": "your_api_token"
}
}
}
}
Restart Claude Desktop after saving.
Claude Code (CLI)
Run once to add the MCP server to your Claude Code config:
claude mcp add hackerone \
-e HACKERONE_API_USERNAME=your_api_token_identifier \
-e HACKERONE_API_TOKEN=your_api_token \
-- node /absolute/path/to/hackerone-mcp/index.js
Or set credentials as shell environment variables first:
export HACKERONE_API_USERNAME=your_api_token_identifier
export HACKERONE_API_TOKEN=your_api_token
claude mcp add hackerone -- node /absolute/path/to/hackerone-mcp/index.js
Verify it's registered:
claude mcp list
Codex CLI
Run once to add the MCP server to Codex:
codex mcp add hackerone \
--env HACKERONE_API_USERNAME=your_api_token_identifier \
--env HACKERONE_API_TOKEN=your_api_token \
-- node /absolute/path/to/hackerone-mcp/index.js
Or configure it directly in config.toml:
- macOS/Linux:
~/.codex/config.toml - Windows:
%USERPROFILE%\.codex\config.toml
[mcp_servers.hackerone]
command = "node"
args = ["/absolute/path/to/hackerone-mcp/index.js"]
[mcp_servers.hackerone.env]
HACKERONE_API_USERNAME = "your_api_token_identifier"
HACKERONE_API_TOKEN = "your_api_token"
Verify it's registered:
codex mcp list
In Codex TUI, run /mcp to view active MCP servers.
Other MCP Clients (generic stdio)
Pass the environment variables when launching:
HACKERONE_API_USERNAME=your_api_token_identifier \
HACKERONE_API_TOKEN=your_api_token \
node /path/to/hackerone-mcp/index.js
Or configure your client's MCP settings with:
- command:
node - args:
["/path/to/hackerone-mcp/index.js"] - env:
{ "HACKERONE_API_USERNAME": "...", "HACKERONE_API_TOKEN": "..." }
Example prompts
Once connected, you can ask your MCP client (Claude, Codex, etc.) things like:
- "List my open HackerOne reports"
- "Show me all critical severity reports"
- "Get the full details of report 12345"
- "What's in scope for the nodejs program?"
- "Show me the policy and bounty info for the security program"
- "List all programs I have access to"
Security Notes
- Never hardcode your API token in the source files
- Always use environment variables or your client's secrets manager
- Your API token provides full access to your HackerOne account — treat it like a password
Reliability settings (optional)
If you see intermittent failures (timeouts, 429 rate limits, transient 5xx), you can tune these environment variables:
HACKERONE_TIMEOUT_MS(default:20000) — per-request timeoutHACKERONE_MAX_RETRIES(default:2) — retries for 429/5xx and transient network errorsHACKERONE_RETRY_BASE_DELAY_MS(default:400) — initial backoff delayHACKERONE_RETRY_MAX_DELAY_MS(default:4000) — maximum backoff delay
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。