p6xer

The P6XER MCP Server exposes machine-readable manifests and a set of tools to interact with Primavera P6 XER files. Built on top of PyP6XER, it offers functions to parse XER files, inspect projects and activities, analyze resources, and perform quality checks on schedules. You can access endpoints and prompts designed for AI models to analyze XER data, generate reports, and drive automated project insights. Typical usage involves starting the MCP server in development mode and invoking tools such as parse_xer_file, get_project_activities, get_critical_path, analyze_resource_utilization, and check_schedule_quality. The server also provides resource and project prompts (xer-project, xer-activities, xer-resources, analyze_xer_project, xer_reporting_prompt) to guide AI-driven analyses and report generation.

Prerequisites:

• Python 3.8+ (recommended 3.10+)
• uv (the Ultralight Virtual environment/uv CLI) installed (as shown in the repository guidelines)
• Git

Install steps:

1. Clone the repository: git clone https://github.com/osama-ata/p6xer-mcp-server.git cd p6xer-mcp-server

2. Install dependencies using uv (recommended): uv sync

   Or install the Python dependencies directly via pip (if you prefer): python -m pip install --upgrade pip python -m pip install mcp[cli] pyp6xer

3. Run the MCP server (development mode): uv run mcp

4. Open the MCP development tools in your browser at http://localhost:8000

Notes:

• Ensure the Python environment has access to any PyP6XER dependencies required by the server.
• The exact command to run may vary depending on your uv setup; the repository documentation shows running the MCP with uv using commands like: uv run --with mcp mcp run server.py
• If you encounter port conflicts, adjust the PORT environment variable or UV configuration accordingly.

Tips and common considerations:

• The server exposes a variety of parsing and analysis tools for XER files; use parse_xer_file for basic project data, get_critical_path to identify schedule risk, and analyze_resource_utilization for resource metrics.
• If running behind a firewall or in a restricted environment, ensure port 8000 (default) is accessible for the MCP UI and API.
• The prompts provided (analyze_xer_project and xer_reporting_prompt) help generate consistent AI-ready prompts for various analysis types such as general, schedule, resources, progress, and quality.
• When upgrading PyP6XER or related dependencies, verify compatibility with the MCP server to avoid API changes.
• For production deployments, consider configuring proper environment variables for port, host, and authentication as needed by your environment.