Planview MCP Server
Provides Planview Enterprise One API access with Okta passwordless authentication, enabling work item and project management, and automated timesheet completion.
README
Planview MCP Server
MCP server for Planview Enterprise One with Okta passwordless authentication and automated timesheet completion.
What This Does
- 🔐 Authenticate to Planview using Okta Verify (no passwords)
- 📊 Access Planview API (work items, projects, users)
- 🤖 Auto-complete timesheets with
/complete-timesheetscommand
Quick Start
Step 1: Clone and Install
git clone <your-repo-url>
cd planview-mcp
npm install
npx playwright install chromium
Step 2: Configure
Linux/macOS:
cp .mcp.json.example .mcp.json
nano .mcp.json # or use any text editor
Windows:
copy .mcp.json.windows.example .mcp.json
notepad .mcp.json # or use any text editor
Edit the env section in .mcp.json with your Planview details:
PLANVIEW_BASE_URL: Your company's Planview URLOKTA_USERNAME: Your email address
Step 3: Authenticate
npm run okta-login
This opens a browser and waits for you to approve the Okta Verify notification on your phone.
Step 4: Build and Restart Claude
npm run build
Then restart Claude Code to load the MCP server.
Usage
Available Commands
| Command | Description |
|---|---|
/complete-timesheets |
Auto-fills all overdue timesheets (8h/day, 40h/week) |
Available Tools
Use these directly in Claude:
planview_get_work_items- List work itemsplanview_get_projects- List projectsplanview_get_current_user- Get your user infoplanview_update_work_item- Update a work itemplanview_execute_request- Make custom API calls
More Examples
See EXAMPLES.md for detailed usage examples including:
- Timesheet automation workflows
- Work item management
- Custom API requests
- Creating your own commands
- Troubleshooting tips
How It Works
This setup uses two MCP servers:
- Planview MCP (this repo) - Handles Planview API and authentication
- Playwright MCP (auto-installed) - Handles browser automation for timesheets
Both are configured in your .mcp.json file. Playwright MCP downloads automatically when Claude starts.
Authentication flow:
- You run
npm run okta-loginonce - Creates
planview-auth.jsonwith your session - Both MCP servers use this session file
- Re-authenticate when session expires
Troubleshooting
| Problem | Solution |
|---|---|
| "Authentication error" | Run npm run okta-login |
| "Can't see browser during login" | Add HEADLESS=true before npm run okta-login |
| Windows npx warning | Use .mcp.json.windows.example (has cmd /c wrapper) |
| "Timesheet automation fails" | Check .mcp.json has both planview and playwright servers |
| "Missing PLANVIEW_BASE_URL" | Check the env section in .mcp.json |
Configuration
Local Setup (Recommended)
Use .mcp.json in this repo directory.
Linux/macOS: Uses npx directly
{
"mcpServers": {
"planview": {
"command": "node",
"args": ["dist/index.js"],
"env": {
"PLANVIEW_BASE_URL": "https://yourcompany.pvcloud.com/planview",
"PLANVIEW_STORAGE_STATE": "planview-auth.json",
"OKTA_USERNAME": "your.email@company.com"
}
},
"playwright": {
"command": "npx",
"args": ["-y", "@playwright/mcp@latest"]
}
}
}
Windows: Requires cmd /c wrapper
{
"mcpServers": {
"planview": {
"command": "node",
"args": ["dist/index.js"],
"env": {
"PLANVIEW_BASE_URL": "https://yourcompany.pvcloud.com/planview",
"PLANVIEW_STORAGE_STATE": "planview-auth.json",
"OKTA_USERNAME": "your.email@company.com"
}
},
"playwright": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@playwright/mcp@latest"]
}
}
}
Global Setup (All Projects)
Add to Claude Code MCP settings with absolute paths.
Linux/macOS:
{
"mcpServers": {
"planview": {
"command": "node",
"args": ["/full/path/to/planview-mcp/dist/index.js"],
"env": {
"PLANVIEW_BASE_URL": "https://yourcompany.pvcloud.com/planview",
"PLANVIEW_STORAGE_STATE": "/full/path/to/planview-mcp/planview-auth.json",
"OKTA_USERNAME": "your.email@company.com"
}
},
"playwright": {
"command": "npx",
"args": ["-y", "@playwright/mcp@latest"]
}
}
}
Windows:
{
"mcpServers": {
"planview": {
"command": "node",
"args": ["C:\\full\\path\\to\\planview-mcp\\dist\\index.js"],
"env": {
"PLANVIEW_BASE_URL": "https://yourcompany.pvcloud.com/planview",
"PLANVIEW_STORAGE_STATE": "C:\\full\\path\\to\\planview-mcp\\planview-auth.json",
"OKTA_USERNAME": "your.email@company.com"
}
},
"playwright": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@playwright/mcp@latest"]
}
}
}
Why Clone Instead of Direct Install?
This MCP requires cloning because:
- Authentication creates
planview-auth.jsonlocally - Both MCP servers need access to the same auth file
- Each company has different Planview URLs
- Configuration is set in
.mcp.json(committed to repo)
Direct GitHub URL installation won't work due to these local file requirements.
Development
npm run dev # Watch mode (auto-rebuild)
npm run build # Build once
npm start # Run server manually
API Documentation
View Planview API docs at: https://yourcompany.pvcloud.com/planview/swagger/index.html
Security
Never commit these files (already in .gitignore):
.mcp.json- Your configuration with credentialsplanview-auth.json- Your session
License
MIT
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.