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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.