uipath -python
Build and host Coded MCP Servers within UiPath
claude mcp add --transport stdio uipath-uipath-mcp-python python server.py
How to use
This UiPath MCP Python SDK enables hosting local MCP servers written in Python. The configuration defines a stdio-based MCP server that runs a Python script (server.py) to communicate with UiPath Platform. Use the CLI to authenticate, initialize, package, and deploy your MCP projects, and run the server locally for development and testing. You can manage multiple MCP servers within a single mcp.json by listing additional server definitions under the servers block, each with its own command and arguments. The provided example shows a server named my-python-server that starts with python server.py. Tools available include the CLI commands for authentication (uipath auth), project initialization (uipath init), local debugging (uipath run), packaging (uipath pack), and publishing (uipath publish).
How to install
Prerequisites:
- Python 3.8+ installed on your system
- pip available to install Python packages
- UiPath UiPath Studio/Orchestrator environment if you plan to deploy to UiPath
Installation steps:
-
Install the MCP SDK package for Python: pip install uipath-mcp
-
Optionally install the UiPath CLI (uv) for packaging and deployment support (as described by the project):
- Install uv usage documentation from UiPath resources
-
Initialize your MCP project structure in your repository:
- Create an mcp.json with your servers definition (example provided in the README)
- Ensure you have a server script (e.g., server.py) that implements the MCP protocol for stdio communication
- Prepare pyproject.toml with metadata if you plan to package via UiPath tooling
-
Authenticate with UiPath (optional if only local testing): uipath auth
-
Run a local server for testing: uv add uipath-mcp uipath init my-python-server uipath run my-python-server
-
Package and publish (optional): uipath pack uipath publish
Additional notes
Tips and common issues:
- Ensure your server.py is accessible from the working directory and that the Python environment has any dependencies installed required by your MCP implementation.
- The mcp.json server entry uses type: stdio in the example; ensure your MCP server adheres to the stdio protocol used by UiPath MCP integration.
- If you need environment variables for authentication or configuration, add an env section under each server entry in mcp.json, e.g., "env": {"UIPATH_API_KEY": "<your-key>"}.
- When packaging, ensure pyproject.toml contains a proper description (avoid &, <, >, ", ', ;) and author information as shown in the README, or packaging may fail.
- For debugging, run the server script directly with Python to verify basic input/output before integrating with UiPath tooling.
Related MCP Servers
web-eval-agent
An MCP server that autonomously evaluates web applications.
django
Django MCP Server is a Django extensions to easily enable AI Agents to interact with Django Apps through the Model Context Protocol it works equally well on WSGI and ASGI
mcp-tool-kit
Agentic abstraction layer for building high precision vertical AI agents written in python for Model Context Protocol.
fhir
FHIR MCP Server – helping you expose any FHIR Server or API as a MCP Server.
unitree-go2
The Unitree Go2 MCP Server is a server built on the MCP that enables users to control the Unitree Go2 robot using natural language commands interpreted by a LLM.
mcp -python-template
This template provides a streamlined foundation for building Model Context Protocol (MCP) servers in Python. It's designed to make AI-assisted development of MCP tools easier and more efficient.