Log inSubmit server
AI AppSec logo

AI AppSec

Evidence-backed AppSec for AI applications and agents. Powered by HAIEC.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install AI AppSec

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "ai-appsec": {
      "command": "npx",
      "args": [
        "-y",
        "ai-appsec"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 1 tools correctly (20d ago).

Overview

Tools1

What AI AppSec lets your agent do. Expand a tool for its parameters.

Verified live~491 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

8/8 checks healthy over the last 62d

What it can do

From the 1 tool this server returned when we ran it; 1 declare their own safety hints.

Runs commands · 1Handles credentials · 1
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age60 days
Maintainers1

Observed 2026-10-19 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 8d ago via OSV.dev · ai-appsec (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars4Stargazers on the source repository.
npm downloads4.3kPackage downloads in the last 30 days.
Last commit5d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed1Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

From the project README

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.

What AI AppSec Does

AI AppSec produces deterministic, reproducible static security evidence for AI-agent and AI-application source code. It uses Semgrep 1.173.0 as its execution engine with a bundled Public Core rulepack (122 detectors, 79 security checks).

Key properties:

  • Static analysis only — does not execute target code
  • No network required for normal scans (Semgrep setup may require network)
  • No HAIEC account or API key required
  • Deterministic evidence — Scan Receipts with SHA-256 digests
  • Fail-closed digests — rulepack/manifest verified at runtime
  • Proof-of-fix — rescan comparison with check-evaluation safety

Quick Start

bash
# Install
npm install -g ai-appsec

# Check Semgrep status
ai-appsec doctor

# Install Semgrep engine (requires network)
ai-appsec setup

# Start MCP server (stdio transport)
ai-appsec

Or use via npx without global install:

Terminal
npx ai-appsec doctor
npx ai-appsec setup

Prerelease channel: @next tracks upcoming prereleases (e.g. ai-appsec@next).

When to Use It

Use scan_ai_security when a developer asks to:

  • "check this for security issues"
  • "audit this task before I push"
  • "review this change for security problems"
  • "scan this AI agent" or "scan this AI app"
  • "check my LLM application"
  • "security review this PR"
  • "is this safe to merge"
  • "check this before deployment"
  • "audit this code for vulnerabilities"
  • "run a security scan"
  • "check for security risks before commit"

scan_ai_security

The MCP tool scan_ai_security is the only tool implemented in v0.1.

It scans AI/LLM/agent application source code for security risks including:

  • Unsafe AI-output execution
  • Secrets exposure
  • RAG/model integration risks
  • Insecure AI API usage
  • Control gaps
  • Prompt/input-related risk signals

What scan_ai_security Does NOT Do

  • Does not provide complete AI system assurance
  • Does not provide runtime behavioral assurance
  • Does not provide compliance certification
  • Does not guarantee zero false positives
  • Does not prove root causes for concern families
  • Does not execute target code, install dependencies, or run package managers
  • Does not perform compliance assessment (compliance requires additional HAIEC evidence)

Findings

Findings are classified by:

  • Finding kind: PRESENCE, RISK_SIGNAL, CONTROL_GAP, VULNERABILITY
  • Severity: CRITICAL, HIGH, MEDIUM, LOW, INFO
  • Disposition: INFORMATIONAL, REVIEW, BLOCK

Security Concern Families

Security Concern Families summarize semantically compatible finding instances for decision-quality presentation. A concern family is a deterministic grouping view — it is NOT necessarily one vulnerability, one material issue, or one root cause. Underlying finding instances remain auditable.

Concern family count is not a vulnerability count. Top 20 / Top 50 are presentation limits, not evidence limits.

COMPLETE / PARTIAL / ERROR

  • COMPLETE: All supported files in scope were successfully analyzed.
  • PARTIAL: Some supported files could not be analyzed (e.g., parser failures). PARTIAL scans cannot prove absence of findings. Missing evidence is never interpreted as PASS.
  • ERROR: The scan could not complete due to an engine error.

Coverage

AI AppSec provides explicit coverage accounting:

  • DISCOVERED: all files found beneath the target
  • INTENTIONALLY_EXCLUDED: files excluded by scope policy
  • UNSUPPORTED: files outside supported extensions (.py, .js, .jsx, .ts, .tsx)
  • TARGETED: supported files intended for analysis
  • ENGINE_REPORTED_SCANNED: files Semgrep reports as scanned
  • PARSE_FAILED: files with parse errors
  • SUCCESSFULLY_ANALYZED: scanned minus parse failures

Scan Receipt

Every scan produces a tamper-evident Scan Receipt with SHA-256 digests for:

  • Finding set
  • Concern family set
  • Coverage file sets
  • Evaluated security checks and detectors
  • Semantic receipt identity

COMPLETE scans produce reproducible receipts across processes and operating systems. PARTIAL scans preserve run-specific coverage differences.

Evidence Envelope

Each scan produces an Evidence Envelope that binds the receipt to the scan execution context, including:

  • Producer identity
  • Target identity (scan input digest, git commit, dirty state)
  • Execution status and completeness
  • Semantic receipt digest
  • Envelope digest

Proof-of-fix

Rescan a target after a fix to compare receipts. The proof-of-fix comparison is safe: it verifies that a specific security check's findings were resolved without requiring the entire scan to be identical.

Offline / Local Operation

Normal scanning operates fully offline after prerequisites are installed:

  • No HAIEC cloud access required
  • No account or API key required
  • No rule download during scanning
  • No telemetry emitted (Semgrep invoked with --metrics off)

Semgrep setup (ai-appsec setup) may require network access to install the engine. Once installed, all scanning is local.

Semgrep Prerequisite

scan_ai_security requires Semgrep 1.173.0 (exact version match).

bash
# Check Semgrep status
ai-appsec doctor

# Install managed Semgrep (requires network)
ai-appsec setup

Semgrep is NOT bundled with this package. It is an external engine installed separately. See THIRD_PARTY_NOTICES.md for details.

Limitations

  • 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)

License

MIT License

Copyright (c) 2026 HAIEC

See LICENSE for the full license text.

Security Reporting

If you believe you have found a security vulnerability:

  1. Do not disclose it publicly before review.
  2. Report via GitHub private vulnerability reporting.
  3. For non-sensitive bugs, use GitHub Issues.

No bug bounty program exists at this time. This project is maintained by a small team. We appreciate responsible disclosure and patience.

Roadmap

Future HAIEC capabilities (not yet implemented in this package):

  • Tenant isolation checking (scan_tenant_isolation)
  • LLM/runtime content verification (verify_llm_content)
  • Deploy security gating (check_deploy_security)
  • Native deterministic dataflow analysis
  • Runtime evidence
  • Inventory evidence
  • Regulatory evidence
  • Compliance/assurance integration
  • Compliance Twin

These will remain independent products/engines. See the HAIEC architecture principle: one workflow, four independent checks.

HAIEC

AI AppSec is powered by HAIEC. HAIEC is the broader assurance platform that may combine ai-appsec evidence with runtime, inventory, regulatory, and external evidence for broader compliance and assurance in the future.

Founder-led development with HAIEC acting as the release gatekeeper for provenance, licensing, and publication.

Related Projects

  • LLMVerify — LLM content verification (independent product, separate repository)
  • Tenant Isolation — Cross-tenant boundary checks (independent product, separate repository)

Built by Subodh Kc — a HAIEC (Human AI Evidence Company) product.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about AI AppSec

AI AppSec is an MCP server that scans AI application and agent source code for security risks using static analysis. It produces deterministic, reproducible evidence with Scan Receipts and SHA-256 digests, using Semgrep and a bundled Public Core rulepack. It does not execute target code or require a HAIEC account or API key.

Install it with npm install -g ai-appsec, then run ai-appsec to start the MCP server over stdio. You can also use npx ai-appsec without a global installation. Run ai-appsec doctor to check Semgrep status and ai-appsec setup to install the Semgrep engine; setup may require network access.

AI AppSec scans AI, LLM, and agent application source code for risks including unsafe AI-output execution, secrets exposure, RAG and model integration risks, insecure AI API usage, control gaps, and prompt or input-related risk signals.

The scan_ai_security tool performs static security analysis of AI application and agent source code; it is the only tool implemented in v0.1. It does not execute target code, install dependencies, run package managers, provide runtime behavioral assurance, certify compliance, or guarantee zero false positives.

Related MCP servers

All in Security All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAI AppSec AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/ai-appsec?style=directory)](https://allmcps.com/mcp/ai-appsec)
HTML Embed
<a href="https://allmcps.com/mcp/ai-appsec"><img src="https://allmcps.com/api/badge/ai-appsec?style=directory" alt="AI AppSec on AllMCPs" /></a>