{
  "markdown": "<p align=\"center\">\n  <img src=\"https://raw.githubusercontent.com/Aakashbhardwaj27/ai-scanner/main/logo.svg\" width=\"80\" alt=\"ai-scanner logo\">\n</p>\n\n<h1 align=\"center\">ai-scanner-mcp</h1>\n\n<p align=\"center\">\n  MCP server for ai-scanner - let AI agents scan codebases for LLM usage, AI frameworks, and exposed secrets.\n</p>\n\n<p align=\"center\">\n  <a href=\"https://opensource.org/licenses/MIT\"><img src=\"https://img.shields.io/badge/License-MIT-yellow.svg\" alt=\"License: MIT\"></a>\n  <a href=\"https://nodejs.org/\"><img src=\"https://img.shields.io/badge/node-≥18-brightgreen.svg\" alt=\"Node.js\"></a>\n  <a href=\"https://modelcontextprotocol.io\"><img src=\"https://img.shields.io/badge/MCP-compatible-blue.svg\" alt=\"MCP\"></a>\n</p>\n\nAn [MCP](https://modelcontextprotocol.io) server that exposes [ai-scanner](https://github.com/Aakashbhardwaj27/ai-scanner) as tools for AI agents. Works with Claude Code, Claude Desktop, Cursor, Windsurf, and any MCP-compatible client.\n\n## Tools\n\n| Tool | Description |\n|---|---|\n| `scan_directory` | Full scan — LLM SDKs, AI frameworks, exposed tokens, and hardcoded secrets with severity levels |\n| `check_secrets` | Security check — pass/fail scan for exposed credentials only. Perfect for pre-commit checks |\n| `ai_inventory` | AI stack overview — which SDKs, frameworks, models, and API endpoints are used (no secret detection) |\n\n## Setup\n\n### Claude Code\n\n```bash\nclaude mcp add ai-scanner npx ai-scanner-mcp\n```\n\n### Claude Desktop\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"ai-scanner\": {\n      \"command\": \"npx\",\n      \"args\": [\"ai-scanner-mcp\"]\n    }\n  }\n}\n```\n\nConfig file location:\n- macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`\n- Windows: `%APPDATA%\\Claude\\claude_desktop_config.json`\n\n### Cursor\n\nAdd to `.cursor/mcp.json` in your project:\n\n```json\n{\n  \"mcpServers\": {\n    \"ai-scanner\": {\n      \"command\": \"npx\",\n      \"args\": [\"ai-scanner-mcp\"]\n    }\n  }\n}\n```\n\n### Windsurf\n\nAdd to `~/.windsurf/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"ai-scanner\": {\n      \"command\": \"npx\",\n      \"args\": [\"ai-scanner-mcp\"]\n    }\n  }\n}\n```\n\n## Example Usage\n\nOnce connected, you can ask your AI agent:\n\n- *\"Scan this project for any exposed API keys\"*\n- *\"Check if there are any hardcoded secrets before I commit\"*\n- *\"What AI SDKs and frameworks does this codebase use?\"*\n- *\"Run a security scan on ./src and tell me if it's safe to push\"*\n- *\"Give me an AI inventory of this project\"*\n\n## Tool Details\n\n### scan_directory\n\nFull scan with all detection categories. Parameters:\n\n| Parameter | Type | Default | Description |\n|---|---|---|---|\n| `directory` | string | *required* | Path to scan |\n| `ai_only` | boolean | `false` | Skip generic secrets (Stripe, GitHub, etc.) |\n| `scan_env` | boolean | `false` | Include .env files |\n| `include_endpoints` | boolean | `true` | Detect LLM API endpoint URLs |\n| `include_models` | boolean | `true` | Detect model name references |\n\n### check_secrets\n\nSecurity-focused pass/fail check. Parameters:\n\n| Parameter | Type | Default | Description |\n|---|---|---|---|\n| `directory` | string | *required* | Path to scan |\n| `ai_only` | boolean | `false` | Only check AI tokens |\n| `scan_env` | boolean | `false` | Include .env files |\n\n### ai_inventory\n\nAI stack awareness (no secret detection). Parameters:\n\n| Parameter | Type | Default | Description |\n|---|---|---|---|\n| `directory` | string | *required* | Path to scan |\n\n## Detection Coverage\n\n- **AI Tokens (20+)** — OpenAI, Anthropic, Google, AWS, HuggingFace, Groq, Replicate, and more\n- **Generic Secrets (59)** — Stripe, Twilio, GitHub, Slack, Discord, database URIs, private keys, JWTs\n- **LLM SDKs (23)** — OpenAI, Anthropic, Google Gemini, LiteLLM, AWS Bedrock, and more\n- **AI Frameworks (24)** — LangChain, LlamaIndex, CrewAI, AutoGen, DSPy, Vercel AI SDK, and more\n- **145 total detection patterns**\n\n## License\n\n[MIT](https://github.com/Aakashbhardwaj27/ai-scanner/blob/main/LICENSE)\n",
  "bytes": 3976,
  "sha": "3b2d6bf96b1f2a7d584f953bf5c480b2e9542ac18b715db2d6832591b1f754cb",
  "repo_slug": "aakashbhardwaj27/ai-scanner-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_aakashbhardwaj27_ai_scanner_b80cdb8d/readme"
}