by adrian-dotco
Integrate with Harvest for easy time recording, project management, and hour tracking using natural language commands.
Allows natural language time tracking in Harvest, automatically parsing entries like 'worked 6 hours on project X today' and handling leave requests.
Harvest is a community-built MCP server published by adrian-dotco that provides AI assistants with tools and capabilities via the Model Context Protocol. Integrate with Harvest for easy time recording, project management, and hour tracking using natural language commands. It is categorized under productivity.
You can install Harvest in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Harvest is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Strong directory entry: Harvest surfaces stars and publisher context so we could sanity-check maintenance before adopting.
Harvest has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
According to our notes, Harvest benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Harvest has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
Useful MCP listing: Harvest is the kind of server we cite when onboarding engineers to host + tool permissions.
Harvest is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Harvest reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
I recommend Harvest for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
According to our notes, Harvest benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Harvest has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
showing 1-10 of 67
An MCP server that lets you log Harvest time entries using natural language, including special handling for leave requests. This server makes time tracking more intuitive by understanding natural language inputs and automatically handling common scenarios like leave requests.
<a href="https://glama.ai/mcp/servers/u2bir05hxy"> <img width="380" height="200" src="https://glama.ai/mcp/servers/u2bir05hxy/badge" alt="Harvest Natural Language Time Entry Server MCP server" /> </a>Install the Claude desktop app
Clone this repository:
git clone https://github.com/adrian-dotco/harvest-mcp-server.git
cd harvest-mcp-server
npm install
npm run build
node build/setup.js
Follow the prompts to enter your:
Restart Claude desktop app
That's it! You can now use natural language time tracking in Claude.
To update to the latest version:
git pull
npm install
npm run build
The setup script will have configured Claude to use your local build of the server, so any updates you pull will be automatically available after rebuilding.
The server provides several tools for interacting with Harvest:
Log time entries using natural language. Examples:
Regular time entries:
"2 hours on Project X doing development work today"
"45 minutes on Project Y testing yesterday"
"3.5 hours on Project Z meetings last Friday"
Leave requests (automatically uses standard work day hours):
"I'm off sick today"
"I'm unwell today"
"Taking annual leave next week"
Get time reports using natural language queries. Examples:
"Show time report for last month"
"Get time summary for this week"
"Show hours from January 1st to January 31st"
"Report time for Q1"
"Show me yesterday's hours"
"Show time report for last month"
"Get project hours for this week"
"Show time report by client for this month"
"Get hours by client for Q1"
"Show time summary by task for January"
"Get task breakdown for last week"
"Show team hours for last week"
"Get time report by user for this month"
List all available Harvest projects:
List my projects
List available tasks for a specific project:
Show tasks for Project X
View recent time entries:
Show my recent time entries
The server supports these environment variables:
HARVEST_ACCESS_TOKEN: Your Harvest personal access tokenHARVEST_ACCOUNT_ID: Your Harvest account IDSTANDARD_WORK_DAY_HOURS: Default hours for a full work day (default: 7.5)TIMEZONE: Your timezone (default: Australia/Perth)The server is built using:
To contribute:
MIT License - see LICENSE for details
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.