Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/woodwosj/GhostShellWrote 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.
[](https://agentmods.dev/mcp/woodwosj/ghostshell/ghostkey)<a href="https://agentmods.dev/mcp/woodwosj/ghostshell/ghostkey"><img src="https://agentmods.dev/badge/mcp/woodwosj/ghostshell/ghostkey/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.
<a href="https://agentmods.dev/mcp/woodwosj/ghostshell/ghostkey"><img src="https://agentmods.dev/badge/mcp/woodwosj/ghostshell/ghostkey.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ghostkey 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 1mo 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.
What it actually says
{ "ghostkey": { "command": "npx", "args": [ "-y", "ghostkey" ] } }
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.
- 1mo ago First seen · 9 lines scan A 405f56a5bf0a
ghostkey is an MCP server published in the GitHub repository woodwosj/GhostShell (1 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-31.
Other mcp servers, from other repositories
homespun
Deploy a multi-user web app from your agent: hosting, auth, database, and permissions. Runs locally from the @homespunapps/mcp npm package. Needs 4 environment variables to run.
cli
Command line interface for the TokPortal public API. Runs locally from the @tokportal/cli npm package.
webhook
Receive, inspect, replay and deliver webhooks — with signature verification and agent triggers. Remote server at mcp.webhook.co.
mcp-server
Unified MCP server for Ignite UI — documentation, API, and CLI scaffolding. Runs locally from the @igniteui/mcp-server npm package.
stockbit-mcp
Indonesian exchange (IDX) via your own Stockbit account: quotes, bandarmology, charts. Unofficial. Runs locally from the stockbit-mcp npm package. Needs 4 environment variables to run.
memi
Memi is the read-only design engineering audit and skill layer for coding agents. Runs locally from the @memi-design/cli npm package.