Skip to main content
MCP server CX Codex

mythos-agent — Claude Code MCP server: what it does, how to install

Reviews codebases for application security vulnerabilities via the Model Context Protocol. Flags logic flaws and builds multi-step attack chains.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add mythos-agent -- npx -y mythos-agent
Open on GitHub

What mythos-agent does

The server evaluates application security by pairing pattern checks with reasoning about logic flaws. It inspects potential race conditions, checks for unverified tokens, and maps how isolated bugs combine into critical attack paths. Instead of scanning for exact syntax matches alone, it locates structural variants of known CVEs across your project files.

The verification pipeline moves through reconnaissance, hypothesis generation, and risk validation. It ships with over 329 rules alongside built-in scanners. Node.js 20 or newer is required.

Running the autonomous hunt workflow requires configuring an AI provider key via init, supporting Anthropic, OpenAI, Ollama, or LM Studio. Without an API key, the server operates strictly in the standard scan mode.

What it helps with

  • find structural variants of specific CVEs across the repository
  • uncover combined attack chains linking injection to data export
  • generate reproduction steps for confirmed code vulnerabilities
  • export security audit findings as SARIF or HTML reports

Example prompts for the agent

  • Run an autonomous security hunt across the project
  • Check the codebase for variants of CVE-2021-44228
  • Ask mythos-agent if there are any authorization bypasses

How to install mythos-agent

Platform CLI

claude mcp add mythos-agent -- npx -y mythos-agent

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about mythos-agent

How to install mythos-agent in Claude Code?

Run claude mcp add mythos-agent -- npx -y mythos-agent in your terminal. You must have Node.js 20 or newer installed on your machine.

What does mythos-agent do?

It inspects codebases for security vulnerabilities, builds hypothesis chains for logic flaws, and suggests code fixes. It can also produce scan reports in terminal, JSON, HTML, and SARIF formats.

Is an external API key necessary to use mythos-agent?

Standard scans run locally without an API key. Autonomous investigation with the hunt command requires configuring an LLM provider such as Anthropic, OpenAI, Ollama, or LM Studio.

Similar MCP servers

Everything for Security →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor