cua-mcp-server 0.1.0__py3-none-any.whl

cua_mcp_server-0.1.0.dist-info/METADATA

@@ -0,0 +1,125 @@
+Metadata-Version: 2.1
+Name: cua-mcp-server
+Version: 0.1.0
+Summary: MCP Server for Computer-Use Agent (CUA)
+Author-Email: TryCua <gh@trycua.com>
+Requires-Python: <3.13,>=3.10
+Requires-Dist: mcp<2.0.0,>=1.6.0
+Requires-Dist: cua-agent<0.2.0,>=0.1.0
+Requires-Dist: cua-computer<0.2.0,>=0.1.0
+Description-Content-Type: text/markdown
+
+<div align="center">
+<h1>
+  <div class="image-wrapper" style="display: inline-block;">
+    <picture>
+      <source media="(prefers-color-scheme: dark)" alt="logo" height="150" srcset="../../img/logo_white.png" style="display: block; margin: auto;">
+      <source media="(prefers-color-scheme: light)" alt="logo" height="150" srcset="../../img/logo_black.png" style="display: block; margin: auto;">
+      <img alt="Shows my svg">
+    </picture>
+  </div>
+
+  [![Python](https://img.shields.io/badge/Python-333333?logo=python&logoColor=white&labelColor=333333)](#)
+  [![macOS](https://img.shields.io/badge/macOS-000000?logo=apple&logoColor=F0F0F0)](#)
+  [![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white)](https://discord.com/invite/mVnXXpdE85)
+  [![PyPI](https://img.shields.io/pypi/v/cua-computer?color=333333)](https://pypi.org/project/cua-computer/)
+</h1>
+</div>
+
+**cua-mcp-server** is a MCP server for the Computer-Use Agent (CUA), allowing you to run CUA through Claude Desktop or other MCP clients.
+### Get started with Agent
+
+## Installation
+
+Install the package from PyPI:
+
+```bash
+pip install cua-mcp-server
+```
+
+This will install:
+- The MCP server
+- CUA agent and computer dependencies 
+- An executable `cua-mcp-server` script in your PATH
+
+## Easy Setup Script
+
+If you want to simplify installation, you can use this one-liner to download and run a setup script:
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/mcp-server/scripts/run_mcp_server.sh | bash
+```
+
+Or use the script directly in your MCP configuration like this:
+
+```json
+{ 
+  "mcpServers": {
+    "cua-agent": {
+      "command": "/bin/bash",
+      "args": ["-c", "curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/mcp-server/scripts/run_mcp_server.sh | bash"],
+      "env": {
+        "CUA_AGENT_LOOP": "OMNI",
+        "CUA_MODEL_PROVIDER": "ANTHROPIC",
+        "CUA_MODEL_NAME": "claude-3-7-sonnet-20250219",
+        "ANTHROPIC_API_KEY": "your-api-key"
+      }
+    }
+  }
+}
+```
+
+This script will automatically check if cua-mcp-server is installed, install it if needed, and run it.
+
+## Claude Desktop Integration
+
+To use with Claude Desktop, add an entry to your Claude Desktop configuration (`claude_desktop_config.json`, typically found in `~/.config/claude-desktop/`):
+
+For more information on MCP with Claude Desktop, see the [official MCP User Guide](https://modelcontextprotocol.io/quickstart/user).
+
+## Cursor Integration
+
+To use with Cursor, add an MCP configuration file in one of these locations:
+
+- **Project-specific**: Create `.cursor/mcp.json` in your project directory
+- **Global**: Create `~/.cursor/mcp.json` in your home directory
+
+After configuration, you can simply tell Cursor's Agent to perform computer tasks by explicitly mentioning the CUA agent, such as "Use the computer control tools to open Safari."
+
+For more information on MCP with Cursor, see the [official Cursor MCP documentation](https://docs.cursor.com/context/model-context-protocol).
+
+### First-time Usage Notes
+
+**API Keys**: Ensure you have valid API keys:
+   - Add your Anthropic API key, or other model provider API key in the Claude Desktop config (as shown above)
+   - Or set it as an environment variable in your shell profile
+
+## Configuration
+
+The server is configured using environment variables (can be set in the Claude Desktop config):
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `CUA_AGENT_LOOP` | Agent loop to use (OPENAI, ANTHROPIC, OMNI) | OMNI |
+| `CUA_MODEL_PROVIDER` | Model provider (ANTHROPIC, OPENAI, OLLAMA, OAICOMPAT) | ANTHROPIC |
+| `CUA_MODEL_NAME` | Model name to use | None (provider default) |
+| `CUA_PROVIDER_BASE_URL` | Base URL for provider API | None |
+| `CUA_MAX_IMAGES` | Maximum number of images to keep in context | 3 |
+
+## Available Tools
+
+The MCP server exposes the following tools to Claude:
+
+1. `run_cua_task` - Run a single Computer-Use Agent task with the given instruction
+2. `run_multi_cua_tasks` - Run multiple tasks in sequence
+
+## Usage
+
+Once configured, you can simply ask Claude to perform computer tasks:
+
+- "Open Chrome and go to github.com"
+- "Create a folder called 'Projects' on my desktop"
+- "Find all PDFs in my Downloads folder"
+- "Take a screenshot and highlight the error message"
+
+Claude will automatically use your CUA agent to perform these tasks.

cua_mcp_server-0.1.0.dist-info/RECORD

@@ -0,0 +1,7 @@
+cua_mcp_server-0.1.0.dist-info/METADATA,sha256=zLOH8ezpPPF07DrAo_fvXdHkaappV_97ypFC_2oBsFE,4716
+cua_mcp_server-0.1.0.dist-info/WHEEL,sha256=tSfRZzRHthuv7vxpI4aehrdN9scLjk-dCJkPLzkHxGg,90
+cua_mcp_server-0.1.0.dist-info/entry_points.txt,sha256=Y3uEunDRfoc-RUDS3HnD942RCxYKquiyk-2HRSqphoc,74
+mcp_server/__init__.py,sha256=G5Bps3KxzYfH79B1TDVQI9vbzjamC_mdgi7GJMgbVcA,575
+mcp_server/__main__.py,sha256=BE2ManEiNpz56nqc7Z_asNjQ6TPtvyu5AbWbyJFePnM,132
+mcp_server/server.py,sha256=RdM0kytzt8uF-vbqPXQ3oay-jtGhum4k_Z0jTDZmfoc,6547
+cua_mcp_server-0.1.0.dist-info/RECORD,,

cua_mcp_server-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: pdm-backend (2.4.4)
+Root-Is-Purelib: true
+Tag: py3-none-any

cua_mcp_server-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,5 @@
+[console_scripts]
+cua-mcp-server = mcp_server.server:main
+
+[gui_scripts]
+

mcp_server/__init__.py

@@ -0,0 +1,19 @@
+"""MCP Server for Computer-Use Agent (CUA)."""
+
+import sys
+import os
+
+# Add detailed debugging at import time
+with open("/tmp/mcp_server_debug.log", "w") as f:
+    f.write(f"Python executable: {sys.executable}\n")
+    f.write(f"Python version: {sys.version}\n")
+    f.write(f"Working directory: {os.getcwd()}\n")
+    f.write(f"Python path:\n{chr(10).join(sys.path)}\n")
+    f.write(f"Environment variables:\n")
+    for key, value in os.environ.items():
+        f.write(f"{key}={value}\n")
+
+from .server import server, main
+
+__version__ = "0.1.0"
+__all__ = ["server", "main"]

mcp_server/__main__.py

@@ -0,0 +1,7 @@
+#!/usr/bin/env python
+"""Entry point for the MCP server module."""
+
+from .server import main
+
+if __name__ == "__main__":
+    main()

mcp_server/server.py

@@ -0,0 +1,193 @@
+import asyncio
+import logging
+import os
+import sys
+import traceback
+from typing import Any, Dict, List, Optional, Union
+
+# Configure logging to output to stderr for debug visibility
+logging.basicConfig(
+    level=logging.DEBUG,  # Changed to DEBUG
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+    stream=sys.stderr,
+)
+logger = logging.getLogger("mcp-server")
+
+# More visible startup message
+logger.debug("MCP Server module loading...")
+
+try:
+    from mcp.server.fastmcp import Context, FastMCP
+
+    logger.debug("Successfully imported FastMCP")
+except ImportError as e:
+    logger.error(f"Failed to import FastMCP: {e}")
+    traceback.print_exc(file=sys.stderr)
+    sys.exit(1)
+
+try:
+    from computer import Computer
+    from agent import ComputerAgent, LLMProvider, LLM, AgentLoop
+
+    logger.debug("Successfully imported Computer and Agent modules")
+except ImportError as e:
+    logger.error(f"Failed to import Computer/Agent modules: {e}")
+    traceback.print_exc(file=sys.stderr)
+    sys.exit(1)
+
+# Global computer instance for reuse
+global_computer = None
+
+
+def get_env_bool(key: str, default: bool = False) -> bool:
+    """Get boolean value from environment variable."""
+    return os.getenv(key, str(default)).lower() in ("true", "1", "yes")
+
+
+def serve() -> FastMCP:
+    """Create and configure the MCP server."""
+    server = FastMCP("cua-agent")
+
+    @server.tool()
+    async def run_cua_task(ctx: Context, task: str) -> str:
+        """
+        Run a Computer-Use Agent (CUA) task and return the results.
+
+        Args:
+            ctx: The MCP context
+            task: The instruction or task for the agent to perform
+
+        Returns:
+            A string containing the agent's response
+        """
+        global global_computer
+
+        try:
+            logger.info(f"Starting CUA task: {task}")
+
+            # Initialize computer if needed
+            if global_computer is None:
+                global_computer = Computer(verbosity=logging.INFO)
+                await global_computer.run()
+
+            # Determine which loop to use
+            loop_str = os.getenv("CUA_AGENT_LOOP", "OMNI")
+            if loop_str == "OPENAI":
+                loop = AgentLoop.OPENAI
+            elif loop_str == "ANTHROPIC":
+                loop = AgentLoop.ANTHROPIC
+            else:
+                loop = AgentLoop.OMNI
+
+            # Determine provider
+            provider_str = os.getenv("CUA_MODEL_PROVIDER", "ANTHROPIC")
+            provider = getattr(LLMProvider, provider_str)
+
+            # Get model name (if specified)
+            model_name = os.getenv("CUA_MODEL_NAME", None)
+
+            # Get base URL for provider (if needed)
+            provider_base_url = os.getenv("CUA_PROVIDER_BASE_URL", None)
+
+            # Create agent with the specified configuration
+            agent = ComputerAgent(
+                computer=global_computer,
+                loop=loop,
+                model=LLM(
+                    provider=provider,
+                    name=model_name,
+                    provider_base_url=provider_base_url,
+                ),
+                save_trajectory=False,
+                only_n_most_recent_images=int(os.getenv("CUA_MAX_IMAGES", "3")),
+                verbosity=logging.INFO,
+            )
+
+            # Collect all results
+            full_result = ""
+            async for result in agent.run(task):
+                logger.info(f"Agent step complete: {result.get('id', 'unknown')}")
+
+                # Add response ID to output
+                full_result += f"\n[Response ID: {result.get('id', 'unknown')}]\n"
+
+                # Extract and concatenate text responses
+                if "text" in result:
+                    # Handle both string and dict responses
+                    text_response = result.get("text", "")
+                    if isinstance(text_response, str):
+                        full_result += f"Response: {text_response}\n"
+                    else:
+                        # If it's a dict or other structure, convert to string representation
+                        full_result += f"Response: {str(text_response)}\n"
+
+                # Log detailed information
+                if "tools" in result:
+                    tools_info = result.get("tools")
+                    logger.debug(f"Tools used: {tools_info}")
+                    full_result += f"\nTools used: {tools_info}\n"
+
+                # Process output if available
+                outputs = result.get("output", [])
+                for output in outputs:
+                    output_type = output.get("type")
+                    if output_type == "reasoning":
+                        logger.debug(f"Reasoning: {output}")
+                        full_result += f"\nReasoning: {output.get('content', '')}\n"
+                    elif output_type == "computer_call":
+                        logger.debug(f"Computer call: {output}")
+                        action = output.get("action", "")
+                        result_value = output.get("result", "")
+                        full_result += f"\nComputer Action: {action}\nResult: {result_value}\n"
+
+                # Add separator between steps
+                full_result += "\n" + "-" * 40 + "\n"
+
+            logger.info(f"CUA task completed successfully")
+            return full_result or "Task completed with no text output."
+
+        except Exception as e:
+            error_msg = f"Error running CUA task: {str(e)}\n{traceback.format_exc()}"
+            logger.error(error_msg)
+            return f"Error during task execution: {str(e)}"
+
+    @server.tool()
+    async def run_multi_cua_tasks(ctx: Context, tasks: List[str]) -> str:
+        """
+        Run multiple CUA tasks in sequence and return the combined results.
+
+        Args:
+            ctx: The MCP context
+            tasks: List of tasks to run in sequence
+
+        Returns:
+            Combined results from all tasks
+        """
+        results = []
+
+        for i, task in enumerate(tasks):
+            logger.info(f"Running task {i+1}/{len(tasks)}: {task}")
+            result = await run_cua_task(ctx, task)
+            results.append(f"Task {i+1}: {task}\nResult: {result}\n")
+
+        return "\n".join(results)
+
+    return server
+
+
+server = serve()
+
+
+def main():
+    """Run the MCP server."""
+    try:
+        logger.debug("Starting MCP server...")
+        server.run()
+    except Exception as e:
+        logger.error(f"Error starting server: {e}")
+        traceback.print_exc(file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()