AI Code Scanner MCP server

by 4hmetuyar·io.github.4hmetuyar/ai-code-scanner·v0.3.2·1 stars

Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection

B78/100grade B

What users say

No reviews yet

Safety scan

B78/100

Adoption

Growing

1 stars537 downloads/wk

Reviews

Nobody has reviewed AI Code Scanner yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

list_patterns
List all AI/LLM security patterns that the scanner can detect, grouped by category (including any custom rules loaded from .guardbee/rules)
scan_directory
Recursively scan a directory for insecure AI/LLM integration patterns. Automatically skips node_modules, .git, dist, and binary files.
scan_file
Scan a single file for insecure AI/LLM integration patterns
scan_text
Scan a text string or code snippet for insecure AI/LLM integration patterns (client-exposed keys, unsafe output handling, excessive agent tool permissions, PII sent to a model, prompt injection surface).

scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it

1 medium

Code scan17 source files scanned20/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 0 days ago15/15
Maintainer identitynamespace and repository owner differ4/10

mediumeval / new Function usedexec.eval

dist/patterns.js: …t", name: "LLM output passed to eval()/Function()", category: "output…

Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

Runs npx -y @guardbee/mcp-ai-code-scanner on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add ai-code-scanner -- npx -y @guardbee/mcp-ai-code-scanner

From the AI Code Scanner repository's README, as published. We do not edit it. Read it on GitHub

🇬🇧 English | 🇹🇷 Türkçe | 🇨🇳 中文

guardbee.ai — AI Security Copilot for websites.

GuardBee's family of MCP (Model Context Protocol) servers — a single monorepo, independent npm packages.

Nothing above is checked by us. What we check is on the safety report.

Is AI Code Scanner MCP server safe?: Mostly: it is graded B (78/100). Read the AI Code Scanner safety report
How do I install AI Code Scanner?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does AI Code Scanner need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is AI Code Scanner maintained?: The last commit was 12 days ago (2026-10-01). The latest release is v0.3.2.
What can I use instead of AI Code Scanner?: Servers from other publishers that do the same job: Agent Security Scanner MCP server, llmtrim MCP server and LLMVerify MCP server. Compare all AI Code Scanner alternatives.

Same job from other publishers: the closest match first, then the best rated.

Agent Security Scanner
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
not reviewed
Established
C
llmtrim
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
not reviewed
Established
A
LLMVerify
Local-first MCP server for LLM output verification — risk signals, injection and PII checks.
not reviewed
Established
B
Agent-Native Analytics
Agent-Native Amplitude/Mixpanel - connect data sources, prompt for charts
not reviewed
Established
A
Godot MCP
Agent-driven Godot playtesting: editor control, input injection, game-time stepping, live state.
not reviewed
Established
A