{
  "markdown": "<p align=\"center\">\n  <h1 align=\"center\">@cocaxcode/ai-context-inspector</h1>\n  <p align=\"center\">\n    <strong>One command. Every AI config in your project. Instantly.</strong><br/>\n    CLI + MCP server &middot; 19 tools detected &middot; Export/Import across 7 targets\n  </p>\n</p>\n\n<p align=\"center\">\n  <a href=\"https://www.npmjs.com/package/@cocaxcode/ai-context-inspector\"><img src=\"https://img.shields.io/npm/v/@cocaxcode/ai-context-inspector.svg?style=flat-square&color=cb3837\" alt=\"npm version\" /></a>\n  <a href=\"https://www.npmjs.com/package/@cocaxcode/ai-context-inspector\"><img src=\"https://img.shields.io/npm/dm/@cocaxcode/ai-context-inspector.svg?style=flat-square\" alt=\"npm downloads\" /></a>\n  <a href=\"https://opensource.org/licenses/MIT\"><img src=\"https://img.shields.io/badge/license-MIT-blue.svg?style=flat-square\" alt=\"License\" /></a>\n  <img src=\"https://img.shields.io/badge/node-%3E%3D20-339933?style=flat-square&logo=node.js&logoColor=white\" alt=\"Node\" />\n  <img src=\"https://img.shields.io/badge/AI%20tools-19%20supported-blueviolet?style=flat-square\" alt=\"19 AI tools\" />\n</p>\n\n<p align=\"center\">\n  <a href=\"#quick-start\">Quick Start</a> &middot;\n  <a href=\"#mcp-server-setup\">MCP Server</a> &middot;\n  <a href=\"#what-it-detects\">What It Detects</a> &middot;\n  <a href=\"#features\">Features</a> &middot;\n  <a href=\"#mcp-tool-reference\">Tool Reference</a> &middot;\n  <a href=\"#architecture\">Architecture</a>\n</p>\n\n---\n\nThe most comprehensive AI ecosystem scanner available. AI Context Inspector discovers every AI configuration file, MCP server, custom skill, agent, and persistent memory in your project — across 19 tools — and gives you the full picture in seconds. Export your entire AI setup and import it into any of 7 supported tools (Claude, Cursor, Windsurf, Copilot, Gemini, Codex, OpenCode) with automatic secret redaction. Zero config. Zero runtime dependencies beyond MCP SDK and Zod. **Everything runs locally — your configs and credentials never leave your machine.**\n\n---\n\n## Quick Start\n\n```bash\nnpx -y @cocaxcode/ai-context-inspector@latest\n```\n\nThat's it. An HTML dashboard opens with everything your AI tools know about your project.\n\n```bash\n# Scan a specific directory\nnpx -y @cocaxcode/ai-context-inspector@latest --dir /path/to/project\n\n# Include user-level configs (~/.claude, ~/.gemini, etc.)\nnpx -y @cocaxcode/ai-context-inspector@latest --user\n\n# Live-connect to each MCP server and list its tools\nnpx -y @cocaxcode/ai-context-inspector@latest --introspect\n\n# Output raw JSON instead of HTML\nnpx -y @cocaxcode/ai-context-inspector@latest --json\n```\n\n<details>\n<summary>All CLI flags</summary>\n\n| Flag | Description | Default |\n|------|-------------|---------|\n| `--dir <path>` | Directory to scan | `.` (current) |\n| `--user` | Include user-level configs (`~/`) | `false` |\n| `--introspect` | Connect to MCP servers and list tools | `false` |\n| `--timeout <ms>` | Introspection timeout per server | `10000` |\n| `--json` | Output JSON instead of HTML | `false` |\n| `--mcp` | Run as MCP server (stdio transport) | `false` |\n\n</details>\n\n---\n\n## MCP Server Setup\n\nRun as an MCP server so your AI tools can inspect their own ecosystem.\n\n### Claude Code\n\n```bash\nclaude mcp add --scope user ai-context-inspector -- npx -y @cocaxcode/ai-context-inspector@latest --mcp\n```\n\n### Claude Desktop\n\nAdd to `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"ai-context-inspector\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@cocaxcode/ai-context-inspector@latest\", \"--mcp\"]\n    }\n  }\n}\n```\n\n<details>\n<summary>Cursor / Windsurf / VS Code / Codex CLI</summary>\n\n**Cursor / Windsurf** — add to `.cursor/mcp.json` or equivalent:\n\n```json\n{\n  \"mcpServers\": {\n    \"ai-context-inspector\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@cocaxcode/ai-context-inspector@latest\", \"--mcp\"]\n    }\n  }\n}\n```\n\n**VS Code** — add to `.vscode/mcp.json`:\n\n```json\n{\n  \"servers\": {\n    \"ai-context-inspector\": {\n      \"type\": \"stdio\",\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@cocaxcode/ai-context-inspector@latest\", \"--mcp\"]\n    }\n  }\n}\n```\n\n**Codex CLI:**\n\n```bash\ncodex mcp add ai-context-inspector -- npx -y @cocaxcode/ai-context-inspector@latest --mcp\n```\n\n</details>\n\nOr add directly to any `.mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"ai-context-inspector\": {\n      \"type\": \"stdio\",\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@cocaxcode/ai-context-inspector@latest\", \"--mcp\"]\n    }\n  }\n}\n```\n\n---\n\n## What It Detects\n\n| Tool | Context Files | What's Found |\n|------|--------------|--------------|\n| **Claude Code** | `CLAUDE.md`, `.claude/`, `.mcp.json` | Instructions, MCP config, skills, agents, memory |\n| **Cursor** | `.cursorrules`, `.cursor/rules/`, `.cursorignore` | Rules, ignore patterns |\n| **Windsurf** | `.windsurfrules`, `.windsurf/rules/` | Codeium/Windsurf rules |\n| **GitHub Copilot** | `.github/copilot-instructions.md`, `.github/agents/` | Instructions, custom agents |\n| **Gemini CLI** | `GEMINI.md`, `.gemini/`, `.geminiignore` | Config, rules |\n| **OpenAI Codex** | `AGENTS.md`, `AGENT.md`, `.codex/` | Agent instructions |\n| **OpenCode** | `OPENCODE.md`, `.opencode/`, `opencode.json` | CLI config |\n| **Aider** | `.aider.conf.yml`, `.aiderignore` | Config, model settings |\n| **Cline** | `.clinerules`, `.clineignore` | Rules (file or directory) |\n| **Roo Code** | `.roo/rules/`, `.roorules`, `.rooignore` | Rules |\n| **Continue.dev** | `.continuerules`, `.continue/config.yaml` | Rules, config |\n| **Amazon Q** | `.amazonq/rules/` | Developer rules |\n| **Augment** | `.augment/rules/`, `.augment-guidelines` | Code rules |\n| **Replit** | `.replit.md` | Agent instructions |\n| **Firebase Studio** | `.idx/airules.md` | AI rules |\n| **VS Code** | `.vscode/mcp.json` | MCP configuration |\n| **Tabnine** | `.tabnine.yaml` | AI config |\n| **Sourcegraph** | `.sourcegraph/` | Cody config |\n| **Universal** | `CONVENTIONS.md` | Multi-tool conventions |\n\n> **Tip:** Pass `--user` to also scan user-level configs: `~/.claude/`, `~/.gemini/`, `~/.codex/`, `~/.continue/`, `~/.aider.conf.yml`, `~/.augment/`, `~/.github/agents/`, `~/.codeium/`, `~/.opencode/`, `~/.tabnine/`.\n\nBeyond context files, the scanner also detects:\n\n- **MCP servers** from `.mcp.json`, `~/.claude.json`, `.vscode/mcp.json`, Claude Desktop config — with optional live introspection\n- **Custom skills** in `.claude/skills/` (including symlinks from `npx skills add`)\n- **Custom agents** in `.claude/agents/` with memory detection\n- **Persistent memories** — Claude Memory, agent memory, engram, OpenSpec, ATL\n\n---\n\n## Features\n\n### Scan\n\n```bash\nnpx -y @cocaxcode/ai-context-inspector@latest\nnpx -y @cocaxcode/ai-context-inspector@latest --user --introspect\n```\n\nGenerates a self-contained HTML dashboard with dark/light mode, search, collapsible sections, file previews, and color-coded tool badges. Pass `--json` for raw output.\n\n### Export\n\n```bash\n# Export your AI ecosystem to .aci/bundle.json\nnpx -y @cocaxcode/ai-context-inspector@latest export\n\n# Export only MCP and context configs, redact secrets\nnpx -y @cocaxcode/ai-context-inspector@latest export --only mcp,context --secrets none\n```\n\n<details>\n<summary>Export flags</summary>\n\n| Flag | Description | Default |\n|------|-------------|---------|\n| `--dir <path>` | Directory to export | `.` |\n| `--output <path>` | Output directory | `.aci/` |\n| `--include-user` | Include user-level configs | `false` |\n| `--only <categories>` | Filter: `mcp,skills,agents,memories,context` | all |\n| `--secrets <mode>` | `none` (redact) or `all` (include) | interactive |\n\n</details>\n\n### Import\n\n```bash\n# Import into a Cursor project\nnpx -y @cocaxcode/ai-context-inspector@latest import --target cursor\n\n# Auto-detect tool, skip confirmation, overwrite existing\nnpx -y @cocaxcode/ai-context-inspector@latest import --yes --force\n```\n\n<details>\n<summary>Import flags</summary>\n\n| Flag | Description | Default |\n|------|-------------|---------|\n| `[file]` | Path to bundle JSON | auto-detect `.aci/bundle.json` |\n| `--dir <path>` | Target directory | `.` |\n| `--target <tool>` | Target tool (see table) | auto-detect |\n| `--scope <scope>` | `project` or `user` | per-resource |\n| `--force` | Overwrite existing resources | `false` |\n| `--yes` | Skip confirmation prompt | `false` |\n| `--only <categories>` | Filter: `mcp,skills,agents,memories,context` | all |\n| `--secrets <mode>` | `none` or `all` | interactive |\n\n</details>\n\n### Supported Import Targets\n\n| Target | MCP Config | Context File | Rules Dir | Skills | Agents |\n|--------|-----------|-------------|-----------|--------|--------|\n| `claude` | `.mcp.json` | `CLAUDE.md` | -- | `.claude/skills/` | `.claude/agents/` |\n| `cursor` | `.cursor/mcp.json` | `.cursorrules` | `.cursor/rules/` | -- | -- |\n| `windsurf` | `.mcp.json` | `.windsurfrules` | `.windsurf/rules/` | -- | -- |\n| `copilot` | `.vscode/mcp.json` | `.github/copilot-instructions.md` | `.github/instructions/` | -- | `.github/agents/` |\n| `gemini` | `.gemini/settings.json` | `GEMINI.md` | `.gemini/rules/` | -- | -- |\n| `codex` | `.mcp.json` | `AGENTS.md` | `.codex/rules/` | -- | -- |\n| `opencode` | `opencode.json` | `OPENCODE.md` | `.opencode/rules/` | -- | -- |\n\n> **Note:** Secrets handling has three modes: **none** (redact all — safe for sharing), **all** (include as-is), or **interactive** (prompt per variable, CLI default). Environment variables in MCP configs are detected automatically.\n\n---\n\n## MCP Tool Reference\n\nWhen running as an MCP server (`--mcp`), five tools are exposed:\n\n### `scan`\n\nDiscover the complete AI ecosystem in a project directory.\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| `directory` | string | No | Path to scan (default: cwd) |\n| `include_user` | boolean | No | Include user-level configs |\n| `introspect` | boolean | No | Live-connect to MCP servers |\n| `timeout` | number | No | Introspection timeout (ms) |\n\n### `introspect_mcp`\n\nConnect to a specific MCP server and list its tools, resources, and prompts.\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| `command` | string | Yes* | Command to launch the server |\n| `args` | string[] | No | Arguments for the command |\n| `env` | object | No | Environment variables |\n| `url` | string | Yes* | URL for HTTP/SSE servers |\n| `transport` | string | No | `stdio` (default) or `http` |\n| `timeout` | number | No | Connection timeout (ms) |\n\n*Either `command` (stdio) or `url` (http) is required.\n\n### `generate_report`\n\nGenerate a standalone HTML dashboard from scan results.\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| `directory` | string | No | Path to scan |\n| `include_user` | boolean | No | Include user-level configs |\n| `introspect` | boolean | No | Introspect MCP servers |\n| `timeout` | number | No | Introspection timeout (ms) |\n\n### `export_ecosystem`\n\nExport the complete AI ecosystem to a portable `.aci/bundle.json`.\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| `dir` | string | No | Directory to scan (default: cwd) |\n| `include_user` | boolean | No | Include user-level configs |\n| `only` | string[] | No | Categories: `mcp`, `skills`, `agents`, `memories`, `context` |\n| `secrets` | string | No | `\"none\"` (default), `\"all\"`, or `[\"VAR1\", \"VAR2\"]` |\n\n### `import_ecosystem`\n\nImport a bundle into a project, adapting configuration to the target tool.\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| `file` | string | No | Path to bundle (auto-detects `.aci/bundle.json`) |\n| `dir` | string | No | Target directory (default: cwd) |\n| `target` | string | No | Target tool (auto-detects): `claude`, `cursor`, `windsurf`, `copilot`, `gemini`, `codex`, `opencode` |\n| `scope` | string | No | `project` or `user` |\n| `force` | boolean | No | Overwrite existing resources |\n| `confirm` | boolean | No | Execute import (default: `false` = dry-run) |\n| `only` | string[] | No | Categories to import |\n| `secrets` | string | No | `\"none\"`, `\"all\"`, `[\"VAR1\"]`, or `{\"VAR1\": \"value\"}` |\n\n> **Warning:** `import_ecosystem` defaults to dry-run mode (`confirm: false`). Set `confirm: true` to actually write files.\n\n---\n\n## Architecture\n\n```\nsrc/\n├── index.ts              # Entry: CLI vs MCP mode routing\n├── cli.ts                # CLI arg parsing + orchestration\n├── server.ts             # createServer() MCP factory\n├── scanner/              # 6 parallel scanners (Promise.all)\n│   ├── catalog.ts        # AI_FILE_CATALOG — 50+ entries, 19 tools\n│   ├── context-files.ts  # Scan .md, rules, configs\n│   ├── mcp-configs.ts    # Parse .mcp.json, ~/.claude.json, etc.\n│   ├── mcp-introspect.ts # Connect to servers, list tools/resources\n│   ├── skills.ts         # Skills + symlinks + frontmatter\n│   ├── agents.ts         # Agents + memory detection\n│   └── memories.ts       # engram, openspec, .atl, claude memory\n├── ecosystem/            # Export/import engine\n│   ├── export.ts         # Scan → bundle → .aci/bundle.json\n│   ├── import.ts         # Load → plan → execute\n│   ├── target-map.ts     # Path configs for 7 AI tools\n│   ├── detect-target.ts  # Auto-detect tool in project\n│   └── secrets.ts        # Env var detection + redaction\n├── report/               # HTML dashboard generator\n│   ├── generator.ts      # generateHtml(ScanResult) → string\n│   ├── sections.ts       # Section renderers\n│   ├── styles.ts         # CSS (dark/light)\n│   └── scripts.ts        # JS (collapse, search, preview)\n└── tools/                # 5 MCP tool handlers\n    ├── scan.ts\n    ├── introspect.ts\n    ├── report.ts\n    ├── export.ts\n    └── import.ts\n```\n\n**Stack:** TypeScript 5 (strict, ESM) / MCP SDK / Zod / tsup / Vitest\n\n---\n\n[MIT](./LICENSE) · Built by [cocaxcode](https://github.com/cocaxcode)\n",
  "bytes": 13852,
  "sha": "5a78aa30ebc88c2cf742f814cfc63233dae181b6bff99d51573ff16edca2efce",
  "repo_slug": "cocaxcode/ai-context-inspector",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_cocaxcode_ai_context_inspector_b541dc7e/readme"
}