AI AppSec MCP Server
Evidence-backed AppSec for AI applications and agents. Powered by HAIEC. Audit AI code for security risks before you commit, push, merge, or deploy. It runs locally over stdio via the published package.
People who work with ai agent security, devsecops and sast and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.
VERIFIED ACTIVE
LAST COMMIT 2026-08-21 · ★ 4 · #13 OF 204 MAINTAINED SECURITY · VERIFIED 2026-09-18
MIT · TypeScript servers · how we verify → /methodology
01 · Install AI AppSec
before you install - you'll need
The README does not document required environment variables for a basic install.
Claude Code
claude mcp add subodhkc-ai-appsec -- npx -y ai-appsec Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"subodhkc-ai-appsec": {
"command": "npx",
"args": [
"-y",
"ai-appsec"
]
}
}
} 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
repo age created 2026-08-16 - young repo, little track record yet
license MIT - declared in the repository
npm package ai-appsec - unscoped; check the name against the project README before installing
registry namespace io.github.subodhkc is GitHub-verified and matches the repo owner
03 · What AI AppSec can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
Limitations (from the README)
- Only scan_ai_security is implemented in v0.1 - Static analysis only - no runtime behavioral evidence - No compliance certification or assessment - No tenant isolation checking (roadmap) - No LLM content verification (roadmap) - No deploy security gating (roadmap)
Latest releases
v0.1.0 · 2026-08-21
AI AppSec v0.1.0 - Release Notes · What AI AppSec Is · AI AppSec is an evidence-backed application security tool for AI applications · and agents. It performs deterministic static analysis on AI-agent and…
04 · Who maintains AI AppSec
AI AppSec is maintained by subodhkc. We track 2 MCP servers from subodhkc - 2 actively maintained, 8 combined GitHub stars, oldest repo from Aug 2026. Full record: all servers from subodhkc.
05 · Facts
- repository
- github.com/subodhkc/ai-appsec
- category
- security - ranked #13 of 204 actively-maintained security servers as of 2026-09-18.
- release cadence
- 1 release in the last 90 days (latest 2026-08-21)
- registry
- io.github.subodhkc/ai-appsec (active, first published 2026-08-21)
- packages
- npm:ai-appsec
06 · AI AppSec FAQ
What is AI AppSec?
Evidence-backed AppSec for AI applications and agents. Powered by HAIEC. Audit AI code for security risks before you commit, push, merge, or deploy. It runs locally over stdio via the published package.
Is AI AppSec still maintained?
Yes - as of 2026-09-18, its last commit was 2026-08-21 and it shipped 1 release in the last 90 days. We re-verify nightly.
How do I install AI AppSec?
Run `npx -y ai-appsec`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.
Does AI AppSec 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 AI AppSec
Alternatives to AI AppSec
Maintained security servers if AI AppSec isn't the fit.
- Treg To OpenRouter for tools and data. Compare catalog providers and call them from one hosted MCP endpoint. ★ 1,627 · 2026-09-18
- SafeDep Vet MCP Protect your AI agents and IDEs from malicious open-source packages. ★ 1,105 · 2026-09-16
- SonarQube MCP Server Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants. ★ 652 · 2026-09-17
- HOL Guard Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server. ★ 625 · 2026-09-18
- Decionis CommerceGate MCP Commerce preflights, D365 authorization, signed evidence, and reports; no marketplace or ERP writes. ★ 533 · 2026-09-18
- Emisar Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step. ★ 353 · 2026-09-15
Pairs well with
Servers that cover what AI AppSec doesn't - only shown when the pairing reason fits the companion.
More security MCP servers · Tenant Isolation · Code Inspectus · Wass MCP · Universal Connector MCP
More TypeScript MCP servers · Search Console MCP · Sudzikcoin MCP Server · SumUp MCP Server · Vulcanus · see all