MCP Server

aict ships a standalone MCP (Model Context Protocol) server binary so AI assistants can call every tool directly — no shell spawning, no output parsing.

Build

go build -o aict-mcp ./cmd/mcp

Configure Claude Desktop

Add to ~/.config/claude/claude_desktop_config.json:

{
  "mcpServers": {
    "aict": {
      "command": "aict-mcp",
      "args": []
    }
  }
}

Configure Cursor

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "aict": {
      "command": "aict-mcp",
      "args": []
    }
  }
}

Available Tools

Once connected, every aict tool becomes a typed, callable function:

ToolDescription
lsDirectory listing
grepPattern search
catFile read
findFilesystem search
statFile metadata
wcLine/word/byte count
diffFile comparison
git statusGit status
git diffGit diff
git logGit log
git ls-filesGit tracked files
git blameGit blame
checksumsHash computation
psProcess list
envEnvironment variables
systemSystem info
doctorSelf-diagnostic

How It Works

  1. The MCP server starts and registers all tool specs
  2. The AI client (Claude, Cursor) discovers available tools
  3. When the model decides to call a tool, it sends a structured request
  4. The server runs the tool, captures structured JSON output, and returns it
  5. The model receives typed data — not raw terminal output

Troubleshooting

IssueFix
Server won’t startEnsure aict-mcp is in your PATH
Tools not showingRestart your AI client after config change
Permission errorsCheck file permissions on target directories