Skip to main content
Glama
P6XER MCP Server

P6XER MCP Server

by osama-ata

P6XER MCP Server

mcp-name: io.github.osama-ata/p6xer-mcp-server

PyPI version Python 3.12+ License: MIT MCP

A full-featured Model Context Protocol (MCP) server for Primavera P6 XER files, built on PyP6XER.

Exposes 13 Tools, 3 Resources, and 2 Prompts so any MCP-compatible AI client (Claude Desktop, Claude Code, Cursor, etc.) can interactively parse, query, and analyze .xer schedule files.


πŸš€ Features

πŸ”§ Tools (13)

Tool

Description

parse_xer_file

Parse an XER file β€” project list, totals, status breakdowns

get_project_activities

Activities with filters: project_id, project_short_name, status, task_type

get_critical_path

Critical path activities (float ≀ 0), sorted by early start

analyze_resource_utilization

Planned/actual hours & costs per resource; over-allocation flags

check_schedule_quality

DCMA-style check: missing logic, long durations, high float, unresourced tasks

get_resources

List resources, optionally filtered by type

get_resource_assignments

Resource–activity assignments with enriched names and costs

get_wbs

Work Breakdown Structure hierarchy

get_relationships

Predecessor/successor relationships enriched with task codes

get_calendars

Calendar definitions with hours-per-period data

get_schedule_summary

At-a-glance stats: counts, date range, critical count

get_earned_value

EVM: PV, EV, AC, CV, SV, CPI, SPI, EAC per project

get_activity_detail

Full detail for one activity (preds + succs + resources)

πŸ“‹ Resources (3)

URI

Description

xer-project://{file_path}/{project_id}

Detailed text summary of a specific project

xer-activities://{file_path}

Activities summary with status breakdown and duration stats

xer-resources://{file_path}

Resources summary with type breakdown and assignment stats

πŸ’¬ Prompts (2)

Prompt

Types

analyze_xer_project

general Β· schedule Β· resources Β· progress Β· quality

xer_reporting_prompt

executive Β· detailed Β· critical_path Β· resource Β· milestone


Related MCP server: project-mcp

οΏ½ Install from Store

Via PyPI (uvx β€” no install needed)

uvx p6xer-mcp-server

Via PyPI (pip)

pip install p6xer-mcp-server
p6xer-mcp-server

Via Smithery

Search for p6xer-mcp-server on smithery.ai and click Install. It will generate the correct Claude Desktop config automatically.

Via GitHub MCP Registry

The server is listed in the GitHub MCP Registry. In Claude Code:

claude mcp add p6xer -- uvx p6xer-mcp-server

Claude Desktop config (after PyPI install)

{
  "mcpServers": {
    "p6xer": {
      "command": "uvx",
      "args": ["p6xer-mcp-server"]
    }
  }
}

οΏ½πŸ“¦ Installation

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

# Install with uv (recommended)
uv sync

# Or with pip
pip install "mcp[cli]>=1.6.0,<2.0.0" pyp6xer

πŸƒ Running

Development / MCP Inspector:

uv run mcp dev src/p6xer_mcp_server/server.py

Stdio (Claude Desktop / Claude Code):

uv run p6xer-mcp-server

πŸ”Œ Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "p6xer": {
      "command": "uvx",
      "args": ["p6xer-mcp-server"]
    }
  }
}

Config file locations:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

  • Linux: ~/.config/Claude/claude_desktop_config.json

πŸ”Œ Claude Code (CLI)

claude mcp add p6xer -- uvx p6xer-mcp-server

πŸ’¬ Example Prompts

Once connected:

Parse project.xer and give me an overview of all projects

What are all the critical path activities, sorted by start date?

Run a DCMA schedule quality check on project.xer

Calculate earned value metrics β€” what are the CPI and SPI?

Show all resource assignments for "John Smith"

What are the predecessors and successors of activity A1000?

List all over-allocated labor resources

Generate an executive summary report for project.xer

πŸ“Š Tool Reference

Filter parameters (most tools accept)

  • project_id – numeric P6 project ID (e.g. "1234")

  • project_short_name – project short name string (e.g. "PROJ1")

Status codes

TK_NotStart Β· TK_Active Β· TK_Complete

Task types

TT_Task Β· TT_Mile Β· TT_FinMile Β· TT_WBS

Resource types

RT_Labor Β· RT_Mat Β· RT_Equip


πŸ—‚οΈ Project Structure

p6xer-mcp-server/
β”œβ”€β”€ src/
β”‚   └── p6xer_mcp_server/
β”‚       β”œβ”€β”€ __init__.py
β”‚       └── server.py       # All tools, resources, and prompts
β”œβ”€β”€ manifest.json           # MCPB bundle manifest
β”œβ”€β”€ mcp.json                # MCP registry metadata
β”œβ”€β”€ smithery.yaml           # Smithery registry configuration
β”œβ”€β”€ pyproject.toml
└── README.md

πŸ“‹ Requirements

  • Python β‰₯ 3.10

  • mcp[cli] >= 1.6.0, < 2.0.0

  • pyp6xer >= 1.16.0


πŸ“„ License

MIT


🚒 Publishing to PyPI (GitHub Actions + Trusted Publishing)

This repository includes a release workflow at .github/workflows/publish-to-pypi.yml based on the PyPA guide and pypa/gh-action-pypi-publish.

1) Configure Trusted Publishers

Create trusted publishers for this exact workflow file:

Use these values:

  • Owner: osama-ata

  • Repository: p6xer-mcp-server

  • Workflow file: publish-to-pypi.yml

  • Environment: pypi (for PyPI), testpypi (for TestPyPI)

  • Project name: p6xer-mcp-server

2) Create GitHub Environments

In repository settings, create two environments:

  • pypi

  • testpypi

Recommended security setup:

  • Require manual approval for pypi

  • No approval required for testpypi

3) Build locally (optional sanity check)

python -m pip install --upgrade build twine
python -m build
python -m twine check dist/*

4) Release flow

  • Push to main: publishes to TestPyPI

  • Push tag v* (for example v0.1.1): publishes to PyPI

git tag v0.1.1
git push origin v0.1.1

Available Tools

13 tools
analyze_resource_utilizationA
Summarize resource utilization: planned/actual hours and costs per resource.
Labor resources (RT_Labor) are flagged as over_allocated if planned hours
exceed max_hours_per_year (default 2080 = 40 hrs/week x 52 weeks).
Results are sorted by planned hours descending.

Inputs: file_path (required), max_hours_per_year.

check_schedule_qualityA
DCMA-style schedule quality check on open/in-progress activities.

Identifies:
- Activities missing predecessors (excluding start milestones)
- Activities missing successors (excluding finish milestones)
- Long-duration activities (threshold: long_duration_days, default 20)
- High-float activities (threshold: high_float_days, default 44)
- TT_Task activities without any resource assignment
- Activities missing early start dates

Inputs: file_path (required), project_id, project_short_name, long_duration_days, +1 more.

get_activity_detailA
Get full detail for a single activity by its task_code (case-insensitive).
Returns all scheduling fields plus enriched predecessors, successors,
and resource assignments with names and costs.

Inputs: file_path (required), task_code (required).

get_calendarsB

List all calendar definitions in the XER file with hours-per-period data.

Inputs: file_path (required).

get_critical_pathA
Find critical path activities (total float <= 0, incomplete only).
Results are sorted by early start date ascending.
Accepts either project_id (numeric) or project_short_name as a filter.

Inputs: file_path (required), project_id, project_short_name.

get_earned_valueC
Calculate Earned Value Management (EVM) metrics per project:
PV (Planned Value), EV (Earned Value), AC (Actual Cost),
CV (Cost Variance), SV (Schedule Variance), CPI, SPI, EAC.

Inputs: file_path (required), project_id, project_short_name.

get_project_activitiesA
Get activities from an XER file.

Filter options:
- project_id: numeric P6 project ID
- project_short_name: project short name string
- status: TK_NotStart | TK_Active | TK_Complete
- task_type: TT_Task | TT_Mile | TT_FinMile | TT_WBS
- limit: max rows returned (default 100)

Inputs: file_path (required), project_id, project_short_name, status, +2 more.

get_relationshipsA
Get activity predecessor/successor relationships, enriched with task codes.
If task_code is supplied, returns only relationships where that activity
appears as the successor or as the predecessor.

Inputs: file_path (required), task_code, limit.

get_resource_assignmentsB
Get resource-activity assignments, enriched with resource and activity names.
- rsrc_name: partial match on resource name (case-insensitive)
- task_code: exact match on activity task code

Inputs: file_path (required), rsrc_name, task_code, limit.

get_resourcesA
List all resources in an XER file.
Optionally filter by type: RT_Labor | RT_Mat | RT_Equip

Inputs: file_path (required), rsrc_type.

get_schedule_summaryC
Comprehensive schedule summary: activity counts by status, critical activity count,
milestone count, resource/calendar/WBS/relationship totals, and date range.

Inputs: file_path (required), project_id, project_short_name.

get_wbsC

Get the Work Breakdown Structure (WBS) hierarchy, optionally filtered by project.

Inputs: file_path (required), project_id, project_short_name.

parse_xer_fileA
Parse a Primavera P6 XER file and return basic project information:
project list with status breakdowns, total activities, resources, calendars,
WBS elements, and relationships.

Inputs: file_path (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 13 tools

    Disambiguation5/5

    Each tool targets a distinct aspect of Primavera P6 XER analysis: resource utilization, schedule quality, activity details, calendars, critical path, earned value, filters, relationships, assignments, resources, summary, WBS, and initial parsing. No overlapping purposes.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern in snake_case (e.g., analyze_resource_utilization, check_schedule_quality, get_activity_detail). The naming is predictable and clear.

    Tool Count5/5

    13 tools is well-scoped for a specialized domain like P6 XER file analysis. Each tool earns its place, covering parsing, activities, resources, schedules, EVM, and WBS without being excessive.

    Completeness5/5

    The tool surface covers the full analysis lifecycle: initial file parsing, detailed views of activities/resources/schedules, critical path, EVM, schedule quality, and summary. No obvious gaps for an analysis-oriented tool.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables AI assistants to analyze Primavera P6 XER files for insights into critical paths, schedule health, and project performance. It provides 23 specialized tools for managing schedule data, resources, and earned value through local or remote interfaces.
      29
      21 PyPI
      16
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      MCP server that enables LLMs to read and analyze Microsoft Project schedules, including critical path, resources, and advanced construction planning layers (AWP and LPS) for work packages and Lean planning.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Read-only MCP server for ProjectLibre .pod files that enables finding project files, summarizing Gantt charts, inspecting tasks, and analyzing schedules without opening ProjectLibre.
      4
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      An MCP server for Microsoft Project that reads, analyzes, and writes .mpp, .xer, and .xml schedule files, offering critical path analysis, DCMA 14-point assessment, and verified writes without requiring Java or Microsoft Project.
      9
      MIT