Does Ghosthunt send my data anywhere?
No. Ghosthunt runs entirely on your local machine. It does not send any data to any server, phone home, track usage, or access the internet. Scan results stay only in your Claude conversation.
@78degrees
基本信息
Find every leaked secret on your machine. Scans .env files, shell history, and config directories for API keys, tokens, and credentials. 35+ patterns including AWS, Stripe, GitHub, OpenAI, and more. Everything runs locally. Zero network calls.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ghosthunt": {
"command": "npx",
"args": [
"-y",
"ghosthunt"
]
}
}
}Scan your entire machine for leaked API keys, tokens, and credentials. Checks .env files, AWS/SSH/Docker/npm configs, shell history, and more. Returns a detailed report with risk explanations, rotation URLs, and fix guidance. Also returns structured JSON data (in a second content block) for visual rendering. If you have visualization capabilities, render the JSON as a visual dashboard with a health score gauge, color-coded finding cards, and auto-fix indicators. Everything runs locally -- no data leaves your machine.
Fix leaked secrets found on your machine. Auto-cleans shell history (backs up first), adds .env to .gitignore where missing, and provides step-by-step rotation instructions with direct links for secrets that need manual rotation. Returns structured JSON (in a second content block) with before/after health scores for visual rendering. If you have visualization capabilities, render the JSON as a fix report dashboard with before/after health score comparison and auto-fixed item list. Run scan_secrets first to see what will be fixed.
Quick health check -- counts how many secrets are on your machine and gives you a health score (0-100). Faster than a full scan. Run scan_secrets for details, or fix_secrets to clean up.
Show GhostHunt version and license status. Displays whether you're on the Free or Pro tier and what Pro includes.
Ghosthunt is an MCP server that scans your development machine for API keys, tokens, and credentials hiding in places like .env files, shell history, AWS/SSH/Docker configs, and more. Everything runs locally with no data leaving your machine.
Add Ghosthunt to your Claude Desktop config by specifying npx -y ghosthunt as the MCP server command, then ask Claude to scan for secrets. You can also run it directly from the terminal via npx ghosthunt. Two tools are available: scan_secrets for a full detailed scan and scan_summary for a quick health check.
.env files under your home directory.No. Ghosthunt runs entirely on your local machine. It does not send any data to any server, phone home, track usage, or access the internet. Scan results stay only in your Claude conversation.
Ghosthunt scans environment files (`.env`, `.env.local`, etc.), AWS credentials, SSH keys, Docker config, npm/PyPI tokens, GitHub CLI OAuth tokens, shell history (`bash`, `zsh`, `fish`), Kubernetes config, netrc passwords, and more than 35 secret patterns including providers like AWS, Stripe, GitHub, OpenAI, Anthropic, Google, Slack, and Twilio.
You can add Ghosthunt to Claude Desktop’s MCP configuration and ask Claude to “scan my machine for leaked secrets”. Alternatively, run `npx ghosthunt` directly from your terminal. Use `scan_secrets` for a full report or `scan_summary` for a quick health check.
Your score starts at 100 and is reduced based on finding severity: critical (−15), high (−8), medium (−3), and low (−1). A score below 50 indicates secrets that need immediate attention.
Rotate critical secrets immediately from the provider’s dashboard. Clear your shell history of sensitive commands. Ensure your `.env` files are in `.gitignore` and audit them for any that should not be committed.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
TestMu AI MCP Server lets developers run, debug, and triage tests through natural language directly from their IDE (Cursor, Claude, GitHub Copilot, and other MCP clients). It exposes five tools — HyperExecute (test orche
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

MCP-first toolbox for agents: namespaced key-value storage, a FIFO queue, auth, and a handful of stateless utility tools (JWT decode, hashing, cert inspection, CIDR math). Free while in early access. This repository is a
评论