Harvest Time Tracking MCP Server
MCP (Model Context Protocol) server for Harvest Time Tracking.
mayank2424
README
Harvest Time Tracking MCP Server
A TypeScript based MCP (Model Context Protocol) server for Harvest time tracking app enabling LLM clients to interact with Harvest account.
Prerequisites
- Bun Runtime
- Harvest account with API access
- API Personal Access Token from Harvest
- Account ID from Harvest
More details on how to create a Personal Access Token can be found in the Harvest API documentation.
Tools
get-company- Get company information- Inputs: None
- Output: Returns Company Information(Name, URL, ID and Currency).
search-clients- Searches for clients in Harvest account- Inputs:
- name: string (optional) - The name of the client to search for.
- isActive: boolean (optional) - Filter clients by their active status.
- Output: Returns a list of clients with IDs and other details.
- Inputs:
get-client- Get client information- Inputs:
- clientId: string - The ID of the client to retrieve.
- Output: Returns detailed information about the specified client.
- Inputs:
search-projects- Searches for projects in Harvest account- Inputs:
- name: string (optional) - The name of the project to search for.
- clientId: string (optional) - The ID of the client to filter projects by.
- isActive: boolean (optional) - Filter projects by their active status.
- Output: Returns a list of projects with IDs and other details.
- Inputs:
get-project- Get project information- Inputs:
- projectId: string - The ID of the project to retrieve.
- Output: Returns detailed information about the specified project.
- Inputs:
list-users- Lists all users in the Harvest account- Inputs: None
- Output: Returns a list of users with IDs and other details.
get-user- Get user information- Inputs:
- userId: string - The ID of the user to retrieve.
- Output: Returns detailed information about the specified user.
- Inputs:
list-project-users- List all project user assignments- Inputs:
- projectId: string - The ID of the project to retrieve users for.
- Output: Returns a list of users assigned to the specified project.
- Inputs:
list-project-tasks- List all project task assignments- Inputs:
- projectId: string - The ID of the project to retrieve tasks for.
- Output: Returns a list of tasks assigned to the specified project. Note: More tools coming soon.
- Inputs:
Usage
Claude Desktop
-
Open the Claude desktop config file
claude-desktop-config.jsonand set the following details undermcpServers.{ "mcpServers": { "Harvest": { "command": "npx", "args": [ "@harvest/mcp-server-typescript", // Or use the path to the local build // "path/to/local/build/dist/index.js" ], "env": { "HARVEST_ACCOUNT_ID": "<Harvest Account ID>", "HARVEST_ACCESS_TOKEN": "<Harvest Personal Access Token>", "HARVEST_BASE_URL": "<Harvest Base URL>" } } } }
Cursor IDE
-
Open the Cursor IDE config file
~/.cursor/mcp.jsonor<project-root>/.cursor/mcp.jsonand set the following details undermcpServers.{ "mcpServers": { "Harvest": { "command": "npx", "args": [ "@harvest/mcp-server-typescript", // Or use the path to the local build // "path/to/local/build/dist/index.js" ], "env": { "HARVEST_ACCOUNT_ID": "<Harvest Account ID>", "HARVEST_ACCESS_TOKEN": "<Harvest Personal Access Token>", "HARVEST_BASE_URL": "<Harvest Base URL>" } } } }
Local Installation And Development
-
Install dependencies:
npm install -
Build the project:
npm run build
This will create a dist directory containing the compiled JavaScript files.
-
To use the local development version of MCP server instead of the published version, you can run the server directly from the local build:
npm run buildModify the MCP server configuration file in any of the clients (Claude, Cursor)
{ "mcpServers": { "Harvest": { "command": "node", "args": [ "path/to/local/build/dist/index.js" ], "env": { "HARVEST_ACCOUNT_ID": "<Harvest Account ID>", "HARVEST_ACCESS_TOKEN": "<Harvest Personal Access Token>", "HARVEST_BASE_URL": "<Harvest Base URL>" } } } } -
Restart the client application (Claude, Cursor) to apply the changes and test the latest changes without publishing a new version.
Recommended Servers
mixpanel
Connect to your Mixpanel data. Query events, retention, and funnel data from Mixpanel analytics.
Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.
MCP PubMed Search
Server to search PubMed (PubMed is a free, online database that allows users to search for biomedical and life sciences literature). I have created on a day MCP came out but was on vacation, I saw someone post similar server in your DB, but figured to post mine.
dbt Semantic Layer MCP Server
A server that enables querying the dbt Semantic Layer through natural language conversations with Claude Desktop and other AI assistants, allowing users to discover metrics, create queries, analyze data, and visualize results.
Crypto Price & Market Analysis MCP Server
A Model Context Protocol (MCP) server that provides comprehensive cryptocurrency analysis using the CoinCap API. This server offers real-time price data, market analysis, and historical trends through an easy-to-use interface.
Nefino MCP Server
Provides large language models with access to news and information about renewable energy projects in Germany, allowing filtering by location, topic (solar, wind, hydrogen), and date range.
Vectorize
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
MATLAB MCP Server
Integrates MATLAB with AI to execute code, generate scripts from natural language, and access MATLAB documentation seamlessly.
Macrostrat MCP Server
Enables Claude to query comprehensive geologic data from the Macrostrat API, including geologic units, columns, minerals, and timescales through natural language.
MCP Word Counter
A Model Context Protocol server that provides tools for analyzing text documents, including counting words and characters. This server helps LLMs perform text analysis tasks by exposing simple document statistics functionality.