Mintmcp Agent Security
MintMCP Agent Security is a Claude Code plugin for the Ship phase that adds hooks to scan for secrets and credentials in Claude Code and Cursor before code leaves your machine.
by mintmcp · github.com/mintmcp/agent-security
Add Claude Code and Cursor hooks that scan for leaked secrets and credentials before agent-written code ships.
Add it to Claude Code
Install the plugin in Claude Code. One command, paste-ready.
/plugin install mintmcp-agent-security@mintmcp/agent-securityBuilt to be called by your agent
Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.
Retrieve this entry with skillselion.get_details("plugin:mintmcp/agent-security") and the paste-ready config with skillselion.get_install_config("plugin:mintmcp/agent-security").
What it does
MintMCP Agent Security is a lightweight Claude Code plugin that installs hooks for secrets scanning in Claude Code and Cursor. Solo builders who let agents write integration code, env samples, or config files face a real risk of pasting live API keys, payment tokens, or cloud credentials into the repo. This plugin focuses on that failure mode with scanner-oriented hooks rather than broad compliance suites. It is beginner-friendly: register the one-plugin bundle, enable hooks, and let scans run as part of normal agent iteration. It pairs naturally with ship-phase review rituals and operate-phase monitoring when you keep the same repo in long-running production. It does not replace full SAST or dependency audit tools; it narrows in on secret leakage at the moment agents produce source. Install when you already use Claude Code or Cursor hooks and want a dedicated guardrail before push or deploy.
Highlights
- Hook-based secrets scanner for Claude Code and Cursor agent sessions.
- Targets common cloud, payment, and provider credential patterns.
- Single-plugin bundle focused on source-level secret detection.
- Fits collaboration workflows where multiple agents touch the same repo.
- Complements manual review with automated scans across edits.
Why builders use it
Agent-assisted coding makes it easy to accidentally commit API keys, payment credentials, and cloud secrets into source files.
After install, hook-driven scans flag common secret patterns across Claude Code and Cursor edits so you fix leaks before ship.
At a glance
- Type - Plugin in Security.
- Adoption - 0 installs, 68 stars, 0 votes.
FAQ
Who is mintmcp-agent-security for?
Indie developers and small teams using Claude Code or Cursor who want automated secrets detection on agent-generated code.
When should I use mintmcp-agent-security?
Enable it before you ship or share repos where agents touch env files, integrations, or payment-related configuration.
How do I add mintmcp-agent-security to my agent?
Install the mintmcp/agent-security plugin from the Claude Code marketplace and configure the documented hooks for Claude Code and Cursor.
Comments
Share how you use mintmcp-agent-security, gotchas, or tips for other indie builders.
No comments yet - be the first to share how you use it.