Mythos Agent MCP Server
AI code-review assistant for application security. Open-source. Reads your code, flags likely security issues, explains its reasoning, suggests fixes. It runs locally over stdio via the published package.
People connecting security tools to Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.
VERIFIED ACTIVE
LAST COMMIT 2026-05-23 · ★ 41 · #96 OF 182 MAINTAINED SECURITY · VERIFIED 2026-08-25
MIT · TypeScript servers · how we verify → /methodology
01 · Install Mythos Agent
before you install - you'll need
The README does not document required environment variables for a basic install.
Claude Code
claude mcp add mythos-agent-mythos-agent -- npx -y mythos-agent Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"mythos-agent-mythos-agent": {
"command": "npx",
"args": [
"-y",
"mythos-agent"
]
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as local process (stdio) - runs on your machine with your user's permissions
license MIT - declared in the repository
npm package mythos-agent - unscoped; check the name against the project README before installing
registry namespace io.github.mythos-agent is GitHub-verified and matches the repo owner
03 · What Mythos Agent can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
Latest releases
v4.3.0 · 2026-05-20
4.3.0 (2026-05-20) · Added · native OpenAI SDK code path + LLMClient abstraction (multi-model stage 2 partial) · wire LLMClient into recon/hypothesis/exploit agents (multi-model stage 2 complete)…
v4.2.0 · 2026-04-26
4.2.0 (2026-04-26) · Added · add baseURL for Anthropic-compatible proxies (multi-model stage 1)
v4.1.0 · 2026-04-26
4.1.0 (2026-04-26) · Added · add CVE replay harness with 5 real GHSA cases · redirect-headers: catch incomplete header strip on cross-host redirect · extract template literals + flag whitespace near interpolation · add…
04 · Who maintains Mythos Agent
mythos-agent is maintained by mythos-agent. It's the only MCP server we track from this author; the repo dates to Apr 2026.
05 · Facts
- repository
- github.com/mythos-agent/mythos-agent
- category
- security - ranked #96 of 182 actively-maintained security servers as of 2026-08-25.
- registry
- io.github.mythos-agent/mythos-agent (active, first published 2026-04-24)
- packages
- npm:mythos-agent
06 · Mythos Agent FAQ
What is Mythos Agent?
AI code-review assistant for application security. Open-source. Reads your code, flags likely security issues, explains its reasoning, suggests fixes. It runs locally over stdio via the published package.
Is Mythos Agent still maintained?
Yes - as of 2026-08-25, its last commit was 2026-05-23. We re-verify nightly.
How do I install Mythos Agent?
Run `npx -y mythos-agent`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.
Does Mythos Agent run locally?
Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.
07 · Alternatives to Mythos Agent
Alternatives to Mythos Agent
Maintained security servers if Mythos Agent isn't the fit.
- SafeDep Vet MCP Protect your AI agents and IDEs from malicious open-source packages. ★ 1,102 · 2026-08-24
- SonarQube MCP Server Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants. ★ 632 · 2026-08-24
- Decionis MCP Server Fail-closed policy gate for AI agent actions, with local evaluation and native pre-tool hooks. ★ 533 · 2026-08-24
- HOL Guard Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server. ★ 470 · 2026-08-25
- Emisar Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step. ★ 409 · 2026-08-23
- Bradesco MCP server for Bradesco - Pix, Cobrança (boleto), Arrecadação, Extrato (OAuth2 + mTLS) ★ 269 · 2026-08-12
Pairs well with
Servers that cover what Mythos Agent doesn't - only shown when the pairing reason fits the companion.
More security MCP servers · Server Malcolm · Repository Intelligence · pdfnative MCP - PDF generation, PAdES signing & introspection · Manifold · SSH MCP Pro
More TypeScript MCP servers · Athena Protocol · Mercury Spec Ops · Better Email MCP · Better Godot MCP · Better Notion MCP · see all