P6XER MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@P6XER MCP Server Parse project.xer and summarize all projects"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
P6XER MCP Server
mcp-name: io.github.osama-ata/p6xer-mcp-server
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.
π Features
π§ Tools (13)
Tool | Description |
| Parse an XER file β project list, totals, status breakdowns |
| Activities with filters: project_id, project_short_name, status, task_type |
| Critical path activities (float β€ 0), sorted by early start |
| Planned/actual hours & costs per resource; over-allocation flags |
| DCMA-style check: missing logic, long durations, high float, unresourced tasks |
| List resources, optionally filtered by type |
| Resourceβactivity assignments with enriched names and costs |
| Work Breakdown Structure hierarchy |
| Predecessor/successor relationships enriched with task codes |
| Calendar definitions with hours-per-period data |
| At-a-glance stats: counts, date range, critical count |
| EVM: PV, EV, AC, CV, SV, CPI, SPI, EAC per project |
| Full detail for one activity (preds + succs + resources) |
π Resources (3)
URI | Description |
| Detailed text summary of a specific project |
| Activities summary with status breakdown and duration stats |
| Resources summary with type breakdown and assignment stats |
π¬ Prompts (2)
Prompt | Types |
|
|
|
|
Related MCP server: project-mcp
οΏ½ Install from Store
Via PyPI (uvx β no install needed)
uvx p6xer-mcp-serverVia PyPI (pip)
pip install p6xer-mcp-server
p6xer-mcp-serverVia 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-serverClaude Desktop config (after PyPI install)
{
"mcpServers": {
"p6xer": {
"command": "uvx",
"args": ["p6xer-mcp-server"]
}
}
}οΏ½π¦ 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" pyp6xerπ Running
Development / MCP Inspector:
uv run mcp dev src/p6xer_mcp_server/server.pyStdio (Claude Desktop / Claude Code):
uv run p6xer-mcp-serverπ 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.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
π Claude Code (CLI)
claude mcp add p6xer -- uvx p6xer-mcp-server㪠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.xerπ Tool Reference
Filter parameters (most tools accept)
project_idβ numeric P6 project ID (e.g."1234")project_short_nameβ 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
ποΈ Project Structure
p6xer-mcp-server/
βββ src/
β βββ p6xer_mcp_server/
β βββ __init__.py
β βββ server.py # All tools, resources, and prompts
βββ manifest.json # MCPB bundle manifest
βββ mcp.json # MCP registry metadata
βββ smithery.yaml # Smithery registry configuration
βββ pyproject.toml
βββ README.mdπ Requirements
Python β₯ 3.10
mcp[cli] >= 1.6.0, < 2.0.0pyp6xer >= 1.16.0
π License
MIT
π’ 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-ataRepository:
p6xer-mcp-serverWorkflow file:
publish-to-pypi.ymlEnvironment:
pypi(for PyPI),testpypi(for TestPyPI)Project name:
p6xer-mcp-server
2) Create GitHub Environments
In repository settings, create two environments:
pypitestpypi
Recommended security setup:
Require manual approval for
pypiNo 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 TestPyPIPush tag
v*(for examplev0.1.1): publishes to PyPI
git tag v0.1.1
git push origin v0.1.1Available Tools
13 toolsanalyze_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 changelogβ¦
TDQS
Scored across 13 tools
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.
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.
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.
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
MCP server for generating rough-draft project plans from natural-language prompts.
Forensic scheduling MCP for Primavera P6 (XER): AACE windows, DCMA-14, Monte Carlo, TIA.
8 MCP servers, 104+ tools: memory, social, PDF, email, images, calendar, scheduler, files.
Remote MCP server to read and edit GanttFather projects: tasks, dates, dependencies, critical path.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables 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.2921 PyPI16MIT
- AlicenseNot gradedqualityCmaintenanceMCP 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
- AlicenseAqualityDmaintenanceRead-only MCP server for ProjectLibre .pod files that enables finding project files, summarizing Gantt charts, inspecting tasks, and analyzing schedules without opening ProjectLibre.4MIT

Horizun Project MCPofficial
AlicenseNot gradedqualityBmaintenanceAn 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.9MIT