projectx-mcp
Enables users to manage time entries and log hours on the ProjectX platform using natural language. It provides tools for creating, viewing, and deleting entries, as well as retrieving a list of available projects.
README
<img src="src/assets/DBP_Logo_Horizontal.svg" alt="Dualboot Partners" width="200" />
projectx-mcp
Log hours in ProjectX by talking to Claude.
"Log 8 hours of Ontrac for today" "Fill in the missing days this week with Ontrac" "Which days am I missing hours for this month?"
Installation (Mac)
1. Download the installer
Download projectx-mcp.pkg from Releases.
2. Install
Double-click the downloaded file and follow the installer steps.
3. Open Claude Desktop
The first time you open Claude Desktop, a browser window will open automatically. Sign in with your Dualboot Google account. The browser closes on its own when done.
That's it. You can now ask Claude to log your hours.
Usage
Just talk to Claude naturally:
Log 8 hours of Ontrac for today with description "Sprint planning"
Check my entries for this week and fill the missing days with 8h of Ontrac
Delete yesterday's entry and log 4h of Internal — Administrative
If login fails or the session expired
Restart Claude Desktop. The browser will open again for you to sign in.
Available tools
| Tool | Description |
|---|---|
get_time_entries |
View entries for a date range |
get_projects |
List available projects |
create_time_entry |
Create an entry |
delete_time_entry |
Delete an entry by ID |
For developers
Architecture
Claude Desktop → MCP Server (stdio) → fetch() + _interslice_session cookie → ProjectX API
Setup from scratch
npm install
npm run build
The session is stored at ~/Library/Application Support/projectx-mcp/auth.json (gitignored).
On startup, if no valid session is found, Chrome opens automatically for login.
Build the installer
npm run build:installer # generates projectx-mcp.pkg
The .pkg installs the app to /usr/local/lib/projectx-mcp/ and automatically writes the Claude Desktop config.
Test the API directly
npm run test:entry
Claude Desktop config (manual)
~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"projectx": {
"command": "/usr/local/bin/projectx-mcp"
}
}
}
Troubleshooting
- Session expired → restart Claude Desktop, the browser opens automatically
- Chrome not found → install Google Chrome
- Project not found → ask Claude to run
get_projectsto see exact names - post-install didn't write the config → manually edit the JSON above
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.