Autopilot Browser MCP Server
Official# Autopilot Browser MCP Server
MCP server for executing Autopilot Browser workflows via Claude Desktop and other AI agents.
## Installation
Add this to your Claude Desktop configuration file:
**MacOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
**Windows**: `%APPDATA%/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"autopilot": {
"command": "npx",
"args": ["-y", "@autopilotbrowser/mcp-server"],
"env": {
"AUTOPILOT_API_KEY": "your_api_key_here"
}
}
}
}
```
## Usage
Once installed, Claude can:
1. Search for available workflows by keyword
2. List all available workflows
3. Execute workflows with the appropriate inputs
### Example Commands
- "Show me all available Autopilot workflows"
- "Search for web scraping workflows"
- "Run the data extraction workflow with URL https://example.com"
## Getting an API Key
Visit [Autopilot Browser](https://autopilotbrowser.com) to sign up and generate your API key.
## Features
- **Workflow Search**: Find workflows by keyword
- **Workflow Execution**: Run automated browser workflows
- **Real-time Results**: Get instant feedback from workflow execution
## Support
For issues or questions:
- Support: nika@autopilotbrowser.com
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: search_workflows is for discovery and information retrieval, while run_workflow is for execution. There is no overlap in functionality, and the descriptions explicitly differentiate them with one being preparatory and the other operational.
Both tools follow a consistent verb_noun naming pattern (search_workflows, run_workflow) with snake_case throughout. The naming is predictable and aligns well with their functions, making them easily distinguishable and readable.
With only 2 tools, the server feels thin for a browser automation domain that typically involves more operations like navigation, clicking, or data extraction. While the tools cover basic workflow execution, the limited count suggests significant gaps in functionality for comprehensive browser control.
The tool set is severely incomplete for a browser automation server. It lacks core operations such as page navigation, element interaction, data scraping, or session management. The existing tools only handle workflow search and execution, leaving most browser automation tasks unsupported and likely causing agent failures.