Summary
This is the X-ray machine for your AI development environment. It scans 19 tools (Claude, Cursor, Windsurf, Copilot, Gemini, and more) to surface every MCP server, skill, agent, memory store, and context file in your project. Run it standalone to generate an HTML dashboard, or wire it in as an MCP server so your AI assistant can introspect its own ecosystem. The export command bundles your entire setup with automatic secret redaction, then import deploys it to a different tool or project. Particularly handy when you're juggling multiple AI toolchains and lose track of which MCP servers are configured where, or when onboarding teammates who need to replicate your exact setup.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
@cocaxcode/ai-context-inspector
One command. Every AI config in your project. Instantly.
CLI + MCP server · 19 tools detected · Export/Import across 7 targets
Quick Start · MCP Server · What It Detects · Features · Tool Reference · Architecture
The 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.
Quick Start
npx -y @cocaxcode/ai-context-inspector@latest
That's it. An HTML dashboard opens with everything your AI tools know about your project.
# Scan a specific directory
npx -y @cocaxcode/ai-context-inspector@latest --dir /path/to/project
# Include user-level configs (~/.claude, ~/.gemini, etc.)
npx -y @cocaxcode/ai-context-inspector@latest --user
# Live-connect to each MCP server and list its tools
npx -y @cocaxcode/ai-context-inspector@latest --introspect
# Output raw JSON instead of HTML
npx -y @cocaxcode/ai-context-inspector@latest --json
All CLI flags
| Flag | Description | Default |
|---|---|---|
--dir <path> | Directory to scan | . (current) |
--user | Include user-level configs (~/) | false |
--introspect | Connect to MCP servers and list tools | false |
--timeout <ms> | Introspection timeout per server | 10000 |
--json | Output JSON instead of HTML | false |
--mcp | Run as MCP server (stdio transport) | false |
MCP Server Setup
Run as an MCP server so your AI tools can inspect their own ecosystem.
Claude Code
claude mcp add --scope user ai-context-inspector -- npx -y @cocaxcode/ai-context-inspector@latest --mcp
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"ai-context-inspector": {
"command": "npx",
"args": ["-y", "@cocaxcode/ai-context-inspector@latest", "--mcp"]
}
}
}
Cursor / Windsurf / VS Code / Codex CLI
Cursor / Windsurf — add to .cursor/mcp.json or equivalent:
{
"mcpServers": {
"ai-context-inspector": {
"command": "npx",
"args": ["-y", "@cocaxcode/ai-context-inspector@latest", "--mcp"]
}
}
}
VS Code — add to .vscode/mcp.json:
{
"servers": {
"ai-context-inspector": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@cocaxcode/ai-context-inspector@latest", "--mcp"]
}
}
}
Codex CLI:
codex mcp add ai-context-inspector -- npx -y @cocaxcode/ai-context-inspector@latest --mcp
Or add directly to any .mcp.json:
{
"mcpServers": {
"ai-context-inspector": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@cocaxcode/ai-context-inspector@latest", "--mcp"]
}
}
}
What It Detects
| Tool | Context Files | What's Found |
|---|---|---|
| Claude Code | CLAUDE.md, .claude/, .mcp.json | Instructions, MCP config, skills, agents, memory |
| Cursor | .cursorrules, .cursor/rules/, .cursorignore | Rules, ignore patterns |
| Windsurf | .windsurfrules, .windsurf/rules/ | Codeium/Windsurf rules |
| GitHub Copilot | .github/copilot-instructions.md, .github/agents/ | Instructions, custom agents |
| Gemini CLI | GEMINI.md, .gemini/, .geminiignore | Config, rules |
| OpenAI Codex | AGENTS.md, AGENT.md, .codex/ | Agent instructions |
| OpenCode | OPENCODE.md, .opencode/, opencode.json | CLI config |
| Aider | .aider.conf.yml, .aiderignore | Config, model settings |
| Cline | .clinerules, .clineignore | Rules (file or directory) |
| Roo Code | .roo/rules/, .roorules, .rooignore | Rules |
| Continue.dev | .continuerules, .continue/config.yaml | Rules, config |
| Amazon Q | .amazonq/rules/ | Developer rules |
| Augment | .augment/rules/, .augment-guidelines | Code rules |
| Replit | .replit.md | Agent instructions |
| Firebase Studio | .idx/airules.md | AI rules |
| VS Code | .vscode/mcp.json | MCP configuration |
| Tabnine | .tabnine.yaml | AI config |
| Sourcegraph | .sourcegraph/ | Cody config |
| Universal | CONVENTIONS.md | Multi-tool conventions |
Tip: Pass
--userto also scan user-level configs:~/.claude/,~/.gemini/,~/.codex/,~/.continue/,~/.aider.conf.yml,~/.augment/,~/.github/agents/,~/.codeium/,~/.opencode/,~/.tabnine/.
Beyond context files, the scanner also detects:
- MCP servers from
.mcp.json,~/.claude.json,.vscode/mcp.json, Claude Desktop config — with optional live introspection - Custom skills in
.claude/skills/(including symlinks fromnpx skills add) - Custom agents in
.claude/agents/with memory detection - Persistent memories — Claude Memory, agent memory, engram, OpenSpec, ATL
Features
Scan
npx -y @cocaxcode/ai-context-inspector@latest
npx -y @cocaxcode/ai-context-inspector@latest --user --introspect
Generates a self-contained HTML dashboard with dark/light mode, search, collapsible sections, file previews, and color-coded tool badges. Pass --json for raw output.
Export
# Export your AI ecosystem to .aci/bundle.json
npx -y @cocaxcode/ai-context-inspector@latest export
# Export only MCP and context configs, redact secrets
npx -y @cocaxcode/ai-context-inspector@latest export --only mcp,context --secrets none
Export flags
| Flag | Description | Default |
|---|---|---|
--dir <path> | Directory to export | . |
--output <path> | Output directory | .aci/ |
--include-user | Include user-level configs | false |
--only <categories> | Filter: mcp,skills,agents,memories,context | all |
--secrets <mode> | none (redact) or all (include) | interactive |
Import
# Import into a Cursor project
npx -y @cocaxcode/ai-context-inspector@latest import --target cursor
# Auto-detect tool, skip confirmation, overwrite existing
npx -y @cocaxcode/ai-context-inspector@latest import --yes --force
Import flags
| Flag | Description | Default |
|---|---|---|
[file] | Path to bundle JSON | auto-detect .aci/bundle.json |
--dir <path> | Target directory | . |
--target <tool> | Target tool (see table) | auto-detect |
--scope <scope> | project or user | per-resource |
--force | Overwrite existing resources | false |
--yes | Skip confirmation prompt | false |
--only <categories> | Filter: mcp,skills,agents,memories,context | all |
--secrets <mode> | none or all | interactive |
Supported Import Targets
| Target | MCP Config | Context File | Rules Dir | Skills | Agents |
|---|---|---|---|---|---|
claude | .mcp.json | CLAUDE.md | -- | .claude/skills/ | .claude/agents/ |
cursor | .cursor/mcp.json | .cursorrules | .cursor/rules/ | -- | -- |
windsurf | .mcp.json | .windsurfrules | .windsurf/rules/ | -- | -- |
copilot | .vscode/mcp.json | .github/copilot-instructions.md | .github/instructions/ | -- | .github/agents/ |
gemini | .gemini/settings.json | GEMINI.md | .gemini/rules/ | -- | -- |
codex | .mcp.json | AGENTS.md | .codex/rules/ | -- | -- |
opencode | opencode.json | OPENCODE.md | .opencode/rules/ | -- | -- |
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.
MCP Tool Reference
When running as an MCP server (--mcp), five tools are exposed:
scan
Discover the complete AI ecosystem in a project directory.
| Parameter | Type | Required | Description |
|---|---|---|---|
directory | string | No | Path to scan (default: cwd) |
include_user | boolean | No | Include user-level configs |
introspect | boolean | No | Live-connect to MCP servers |
timeout | number | No | Introspection timeout (ms) |
introspect_mcp
Connect to a specific MCP server and list its tools, resources, and prompts.
| Parameter | Type | Required | Description |
|---|---|---|---|
command | string | Yes* | Command to launch the server |
args | string[] | No | Arguments for the command |
env | object | No | Environment variables |
url | string | Yes* | URL for HTTP/SSE servers |
transport | string | No | stdio (default) or http |
timeout | number | No | Connection timeout (ms) |
*Either command (stdio) or url (http) is required.
generate_report
Generate a standalone HTML dashboard from scan results.
| Parameter | Type | Required | Description |
|---|---|---|---|
directory | string | No | Path to scan |
include_user | boolean | No | Include user-level configs |
introspect | boolean | No | Introspect MCP servers |
timeout | number | No | Introspection timeout (ms) |
export_ecosystem
Export the complete AI ecosystem to a portable .aci/bundle.json.
| Parameter | Type | Required | Description |
|---|---|---|---|
dir | string | No | Directory to scan (default: cwd) |
include_user | boolean | No | Include user-level configs |
only | string[] | No | Categories: mcp, skills, agents, memories, context |
secrets | string | No | "none" (default), "all", or ["VAR1", "VAR2"] |
import_ecosystem
Import a bundle into a project, adapting configuration to the target tool.
| Parameter | Type | Required | Description |
|---|---|---|---|
file | string | No | Path to bundle (auto-detects .aci/bundle.json) |
dir | string | No | Target directory (default: cwd) |
target | string | No | Target tool (auto-detects): claude, cursor, windsurf, copilot, gemini, codex, opencode |
scope | string | No | project or user |
force | boolean | No | Overwrite existing resources |
confirm | boolean | No | Execute import (default: false = dry-run) |
only | string[] | No | Categories to import |
secrets | string | No | "none", "all", ["VAR1"], or {"VAR1": "value"} |
Warning:
import_ecosystemdefaults to dry-run mode (confirm: false). Setconfirm: trueto actually write files.
Architecture
src/
├── index.ts # Entry: CLI vs MCP mode routing
├── cli.ts # CLI arg parsing + orchestration
├── server.ts # createServer() MCP factory
├── scanner/ # 6 parallel scanners (Promise.all)
│ ├── catalog.ts # AI_FILE_CATALOG — 50+ entries, 19 tools
│ ├── context-files.ts # Scan .md, rules, configs
│ ├── mcp-configs.ts # Parse .mcp.json, ~/.claude.json, etc.
│ ├── mcp-introspect.ts # Connect to servers, list tools/resources
│ ├── skills.ts # Skills + symlinks + frontmatter
│ ├── agents.ts # Agents + memory detection
│ └── memories.ts # engram, openspec, .atl, claude memory
├── ecosystem/ # Export/import engine
│ ├── export.ts # Scan → bundle → .aci/bundle.json
│ ├── import.ts # Load → plan → execute
│ ├── target-map.ts # Path configs for 7 AI tools
│ ├── detect-target.ts # Auto-detect tool in project
│ └── secrets.ts # Env var detection + redaction
├── report/ # HTML dashboard generator
│ ├── generator.ts # generateHtml(ScanResult) → string
│ ├── sections.ts # Section renderers
│ ├── styles.ts # CSS (dark/light)
│ └── scripts.ts # JS (collapse, search, preview)
└── tools/ # 5 MCP tool handlers
├── scan.ts
├── introspect.ts
├── report.ts
├── export.ts
└── import.ts
Stack: TypeScript 5 (strict, ESM) / MCP SDK / Zod / tsup / Vitest
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →