automation-anywhere-mcp
Integrates Claude Desktop with Automation Anywhere Community Edition via FastMCP, enabling AI-driven listing and execution of RPA bots through natural language commands.
README
š¤ AI-Powered RPA Orchestration
Claude Desktop (MCP) + FastMCP + Automation Anywhere Community Edition
This project demonstrates how to integrate Claude Desktop (via MCP) with Automation Anywhere Community Edition using a custom FastMCP Python server.
Claude acts as the decision engine, and Python executes real RPA automations through Automation Anywhere Control Room APIs.
š Architecture
Claude Desktop (MCP Client)
ā¬
FastMCP Python Server (Custom Tools)
ā¬
Automation Anywhere Control Room REST API
ā¬
Bot Execution
šÆ Features
- š¹ AI-driven automation triggering
- š¹ Dynamic bot listing from Control Room
- š¹ Supports both Manually and Automatic bot selection & execution
- š¹ MCP tool integration with Claude Desktop
- š¹ Secure environment variable handling
- š¹ REST API authentication with Control Room
- š¹ Modular and extensible structure
š ļø Tech Stack
- Python 3.10+
- FastMCP
- Claude Desktop (MCP enabled)
- Automation Anywhere Community Edition
- uv (dependency management)
š¬ Example Usage in Claude Desktop
User prompt:
Run the invoice processing automation
Claude will:
- List AA bots
list_bots - Identify relevant bot
- Call
run_bot - Trigger execution
No hardcoded bot IDs required.
š§© Claude Desktop MCP Configuration
To connect Claude Desktop to this FastMCP server, update your Claude Desktop MCP configuration file.
š Locate Claude Desktop Config File
Open Claude Desktop ā Settings ā Developer ā MCP Configuration
Add the following configuration:
{
"mcpServers": {
"automation-anywhere": {
"command": "ADD_PATH\\.venv\\Scripts\\python.exe",
"args": [
"ADD_PATH\\main.py"
]
}
},
"preferences": {
"coworkScheduledTasksEnabled": false,
"sidebarMode": "chat",
"coworkWebSearchEnabled": true
}
}
ā ļø Important
Replace:
ADD_PATH with your actual project directory path.
Example (Windows):
"command": "C:\\Users\\YourName\\AA_MCP\\.venv\\Scripts\\python.exe",
"args": [
"C:\\Users\\YourName\\AA_MCP\\main.py"
]
For macOS:
"command": "/Users/yourname/AA_MCP/.venv/bin/python",
"args": [
"/Users/yourname/AA_MCP/main.py"
]
š After Updating
Save the configuration
Restart Claude Desktop
Your MCP server should now appear as:
automation-anywhere
Claude can now call:
list_bots
run_bot
ā
Verify Connection
In Claude Desktop, try:
List Automation anywhere bot
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.