AI Scanner
Scan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
ai-scanner-mcpclaude mcp add ai-scanner -- npx -y ai-scanner-mcp@1.0.3
{
"mcpServers": {
"ai-scanner": {
"command": "npx",
"args": [
"-y",
"ai-scanner-mcp@1.0.3"
]
}
}
}
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
ai-scanner-mcp
MCP server for ai-scanner - let AI agents scan codebases for LLM usage, AI frameworks, and exposed secrets.
An MCP server that exposes ai-scanner as tools for AI agents. Works with Claude Code, Claude Desktop, Cursor, Windsurf, and any MCP-compatible client.
Tools
| Tool | Description |
|---|---|
scan_directory | Full scan — LLM SDKs, AI frameworks, exposed tokens, and hardcoded secrets with severity levels |
check_secrets | Security check — pass/fail scan for exposed credentials only. Perfect for pre-commit checks |
ai_inventory | AI stack overview — which SDKs, frameworks, models, and API endpoints are used (no secret detection) |
Setup
Claude Code
claude mcp add ai-scanner npx ai-scanner-mcp
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ai-scanner": {
"command": "npx",
"args": ["ai-scanner-mcp"]
}
}
}
Config file location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Cursor
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"ai-scanner": {
"command": "npx",
"args": ["ai-scanner-mcp"]
}
}
}
Windsurf
Add to ~/.windsurf/mcp.json:
{
"mcpServers": {
"ai-scanner": {
"command": "npx",
"args": ["ai-scanner-mcp"]
}
}
}
Example Usage
Once connected, you can ask your AI agent:
- "Scan this project for any exposed API keys"
- "Check if there are any hardcoded secrets before I commit"
- "What AI SDKs and frameworks does this codebase use?"
- "Run a security scan on ./src and tell me if it's safe to push"
- "Give me an AI inventory of this project"
Tool Details
scan_directory
Full scan with all detection categories. Parameters:
| Parameter | Type | Default | Description |
|---|---|---|---|
directory | string | required | Path to scan |
ai_only | boolean | false | Skip generic secrets (Stripe, GitHub, etc.) |
scan_env | boolean | false | Include .env files |
include_endpoints | boolean | true | Detect LLM API endpoint URLs |
include_models | boolean | true | Detect model name references |
check_secrets
Security-focused pass/fail check. Parameters:
| Parameter | Type | Default | Description |
|---|---|---|---|
directory | string | required | Path to scan |
ai_only | boolean | false | Only check AI tokens |
scan_env | boolean | false | Include .env files |
ai_inventory
AI stack awareness (no secret detection). Parameters:
| Parameter | Type | Default | Description |
|---|---|---|---|
directory | string | required | Path to scan |
Detection Coverage
- AI Tokens (20+) — OpenAI, Anthropic, Google, AWS, HuggingFace, Groq, Replicate, and more
- Generic Secrets (59) — Stripe, Twilio, GitHub, Slack, Discord, database URIs, private keys, JWTs
- LLM SDKs (23) — OpenAI, Anthropic, Google Gemini, LiteLLM, AWS Bedrock, and more
- AI Frameworks (24) — LangChain, LlamaIndex, CrewAI, AutoGen, DSPy, Vercel AI SDK, and more
- 145 total detection patterns
License
Frequently asked questions
What is AI Scanner?
Scan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets.
How do I install AI Scanner?
It runs on your machine. In Claude Code: claude mcp add ai-scanner -- npx -y ai-scanner-mcp@1.0.3. For other clients, paste the JSON configuration from this page into their MCP settings.
Does AI Scanner need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is AI Scanner open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains AI Scanner?
It is published by Aakashbhardwaj27. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.