hackerone-brain-mcp-server

hackerone-brain-mcp-server is a skill for Claude Code, Codex from ShulkwiSEC/bb-huge. It costs 49 tokens per session (2,400 once invoked), scanned A, original, MIT.

An integration guide for connecting an MCP server to HackerOne, a platform for coordinated vulnerability disclosure and bug bounty programs. It retrieves program rules, target scope, and previously disclosed reports for use in an agent's context.

In plain words
What is it for?
Use it when preparing for a HackerOne program, reviewing its policies and scope, checking related reports, and identifying which vulnerability types may be rewarded.
Why use it?
It helps prevent testing outside a program's permitted scope and reduces the chance of reporting an issue that has already been disclosed. It puts program-specific information beside the security work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - [`_shared/references/elite-chaining-strategy.md`](../_shared/references/elite-chaining-strategy.md) — Exploit chaining methodology and high-payout chain patte.

Good fit Use it when preparing for a HackerOne program, reviewing its policies and scope, checking related reports, and identifying which vulnerability types may be rewarded.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ShulkwiSEC/bb-huge
agentmods
npx agentmods add skills/shulkwisec/bb-huge/hackerone-brain-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for hackerone-brain-mcp-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/shulkwisec/bb-huge/hackerone-brain-mcp/github.svg)](https://agentmods.dev/skills/shulkwisec/bb-huge/hackerone-brain-mcp)
Your own site
<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/hackerone-brain-mcp"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/hackerone-brain-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for hackerone-brain-mcp-server

Your own site · 80×15
<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/hackerone-brain-mcp"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/hackerone-brain-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,400 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.02400
Opus 5 $0.00024 $0.01200
Sonnet 5 $0.00010 $0.00480
Haiku 4.5 $0.00005 $0.00240

Measured 7d ago against content hash 018f4ce030c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

hackerone-brain-mcp-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/curated/hackerone-brain-mcp/SKILL.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HackerOne Brain (H1 Brain) MCP Server

When to Use

  • When starting a new bug bounty program and need to pull scope/policy into .claudemd.
  • When checking disclosed reports to avoid submitting duplicates.
  • When researching what vulnerability types a program rewards highest.
  • When building target-specific context for Claude's autonomous hunting sessions.

Prerequisites

  • HackerOne API token (from HackerOne settings → API → Generate Token)
  • Node.js 18+ installed
  • Claude Code CLI with MCP server support enabled
  • H1_API_TOKEN environment variable set

Core Concept

"H1 Brain is an MCP Server that pulls HackerOne program policy and disclosed reports directly into Claude's context." — Episode 166 [32:02]

MCP (Model Context Protocol) servers extend Claude's capabilities by providing structured access to external data sources. H1 Brain connects Claude to HackerOne's platform data.

Workflow

Phase 1: MCP Server Setup

Add H1 Brain to your Claude Code CLI MCP configuration:

// ~/.claude/mcp_servers.json
{
  "h1-brain": {
    "command": "npx",
    "args": ["-y", "h1-brain-mcp"],
    "env": {
      "H1_API_TOKEN": "${H1_API_TOKEN}"
    }
  }
}

If the h1-brain-mcp package is not available publicly, build a custom MCP server:

// mcp-servers/h1-brain/index.ts
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

const H1_API_BASE = "https://api.hackerone.com/v1";
const H1_TOKEN = process.env.H1_API_TOKEN;

const server = new Server({ name: "h1-brain", version: "1.0.0" }, {
  capabilities: { tools: {} },
});

// Tool: Get program policy and scope
server.setRequestHandler("tools/list", async () => ({
  tools: [
    {
      name: "get_program_policy",
      description: "Get a HackerOne program's policy, scope, and bounty table",
      inputSchema: {
        type: "object",
        properties: { handle: { type: "string", description: "Program handle (e.g., 'github')" } },
        required: ["handle"],
      },
    },
    {
      name: "search_disclosed_reports",
      description: "Search publicly disclosed reports for a program",
      inputSchema: {
        type: "object",
        properties: {
          handle: { type: "string" },
          query: { type: "string", description: "Search query (e.g., 'SSRF', 'IDOR')" },
        },
        required: ["handle"],
      },
    },
  ],
}));

server.setRequestHandler("tools/call", async (request) => {
  const { name, arguments: args } = request.params;

  if (name === "get_program_policy") {
    const res = await fetch(`${H1_API_BASE}/hackerone/programs/${args.handle}`, {
      headers: { Authorization: `Bearer ${H1_TOKEN}` },
    });
    const data = await res.json();
    return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] };
  }

  if (name === "search_disclosed_reports") {
    const res = await fetch(
      `${H1_API_BASE}/reports?filter[program][]=${args.handle}&filter[disclosed]=true&page[size]=20`,
      { headers: { Authorization: `Bearer ${H1_TOKEN}` } }
    );
    const data = await res.json();
    return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] };
  }

  return { content: [{ type: "text", text: "Unknown tool" }] };
});

const transport = new StdioServerTransport();
server.connect(transport);

Read the full file on GitHub · 280 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 280 lines · 49 tokens per session scan A 018f4ce030c5

Subscribe to this mod's changes

hackerone-brain-mcp-server is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 2,400 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.