Fix mcp-server documentation

This commit is contained in:
Morgan Dean
2025-07-10 15:03:57 -07:00
parent 9f2aa0fc0b
commit 20dd3f50c3
+73 -78
View File
@@ -33,13 +33,24 @@ Before installing the MCP server, ensure you have:
2. **macOS CUA image** pulled and ready
3. **Python 3.10+** installed on your system
<Callout type="info">
Follow our [C/ua Usage Guide](../guides/cua-usage-guide.mdx) for help setting
everything up.
</Callout>
### Install via pip
```bash
pip install cua-mcp-server
```
### Quick Setup Script
This will install:
- The MCP server
- CUA agent and computer dependencies
- An executable `cua-mcp-server` script in your PATH
### Install Script
For automated installation, use our setup script:
@@ -56,11 +67,7 @@ This script:
## Getting Started
<Steps>
<Step>
### Configure Claude Desktop
Add the MCP server to your Claude Desktop configuration:
You can then use the script in your MCP configuration like this:
```json
{
@@ -71,36 +78,47 @@ Add the MCP server to your Claude Desktop configuration:
"env": {
"CUA_AGENT_LOOP": "OMNI",
"CUA_MODEL_PROVIDER": "ANTHROPIC",
"CUA_PROVIDER_API_KEY": "your-anthropic-api-key"
"CUA_MODEL_NAME": "claude-3-7-sonnet-20250219",
"CUA_PROVIDER_API_KEY": "your-api-key"
}
}
}
}
```
<Callout type="tip">
The configuration file is typically located at
`~/.config/claude-desktop/claude_desktop_config.json`
</Callout>
</Step>
### Development Config
<Step>
### Start Using CUA
If you want to develop with the cua-mcp-server directly without installation, you can use this configuration:
Once configured, you can ask Claude to perform computer tasks:
```text
"Take a screenshot of the current screen"
"Open Safari and navigate to google.com"
"Click on the search bar and type 'weather'"
```json
{
"mcpServers": {
"cua-agent": {
"command": "/bin/bash",
"args": ["~/cua/libs/python/mcp-server/scripts/start_mcp_server.sh"],
"env": {
"CUA_AGENT_LOOP": "UITARS",
"CUA_MODEL_PROVIDER": "OAICOMPAT",
"CUA_MODEL_NAME": "ByteDance-Seed/UI-TARS-1.5-7B",
"CUA_PROVIDER_BASE_URL": "https://****************.us-east-1.aws.endpoints.huggingface.cloud/v1",
"CUA_PROVIDER_API_KEY": "your-api-key"
}
}
}
}
```
</Step>
This configuration:
<Step>
### Configure Environment Variables
- Uses the start_mcp_server.sh script which automatically sets up the Python path and runs the server module
- Works with Claude Desktop, Cursor, or any other MCP client
- Automatically uses your development code without requiring installation
Customize the MCP server behavior with these environment variables:
Just add this to your MCP client's configuration and it will use your local development version of the server.
### Environment Variables
The MCP server is configured using the following environment variables.
| Variable | Description | Default |
| ----------------------- | ----------------------------------------------------- | ----------------------- |
@@ -110,74 +128,51 @@ Customize the MCP server behavior with these environment variables:
| `CUA_PROVIDER_BASE_URL` | Base URL for provider API | None |
| `CUA_MAX_IMAGES` | Maximum number of images to keep in context | 3 |
</Step>
</Steps>
### Usage
## Examples
Once configured, you can simply ask the model to perform computer tasks:
### Basic Computer Control
- "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"
```python
# Example prompt to Claude
"Take a screenshot and save it to the desktop"
The model will automatically use your CUA agent to perform these tasks.
# Claude will use the run_cua_task tool:
# {
# "instruction": "Take a screenshot and save it to the desktop",
# "display": "1920x1080"
# }
```
## Available Tools
### Multi-Step Automation
The MCP server exposes the following tools to Claude:
```python
# Example prompt to Claude
"Open a new browser window, navigate to github.com, and search for 'cua'"
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
# Claude will use the run_multi_cua_tasks tool with multiple instructions
```
## Integrations
### Integrating with Cursor
### Claude Desktop
Create a configuration file at `~/.cursor/mcp.json` or `.cursor/mcp.json` in your project:
To use with Claude Desktop, add an entry to your Claude Desktop configuration (`claude_desktop_config.json`, typically found in `~/.config/claude-desktop/`):
```json
{
"mcpServers": {
"cua-agent": {
"command": "/bin/bash",
"args": ["~/.cua/start_mcp_server.sh"],
"env": {
"CUA_AGENT_LOOP": "OMNI",
"CUA_MODEL_PROVIDER": "ANTHROPIC",
"CUA_PROVIDER_API_KEY": "your-api-key"
}
}
}
}
```
For more information on MCP with Claude Desktop, see the [official MCP User Guide](https://modelcontextprotocol.io/quickstart/user).
### Development Mode
### Cursor
For local development without installation:
To use with Cursor, add an MCP configuration file in one of these locations:
```json
{
"mcpServers": {
"cua-agent": {
"command": "/bin/bash",
"args": ["~/cua/libs/mcp-server/scripts/start_mcp_server.sh"],
"env": {
"CUA_AGENT_LOOP": "OMNI",
"CUA_MODEL_PROVIDER": "ANTHROPIC",
"CUA_PROVIDER_API_KEY": "your-api-key"
}
}
}
}
```
- **Project-specific**: Create `.cursor/mcp.json` in your project directory
- **Global**: Create `~/.cursor/mcp.json` in your home directory
### Troubleshooting
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).
## Troubleshooting
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
If you get a `/bin/bash: ~/cua/libs/python/mcp-server/scripts/start_mcp_server.sh: No such file or directory` error, try changing the path to the script to be absolute instead of relative.
View MCP server logs: