autotask
MCP server for Kaseya Autotask PSA — 39 tools for companies, tickets, projects, time entries, and more
claude mcp add --transport stdio asachs01-autotask-mcp node /path/to/autotask-mcp/dist/entry.js \ --env AUTOTASK_SECRET="your-secret" \ --env AUTOTASK_USERNAME="your-user@company.com" \ --env AUTOTASK_INTEGRATION_CODE="your-code"
How to use
Autotask MCP Server provides a structured MCP interface to access Kaseya Autotask PSA data and operations. It exposes a suite of tools that cover core entities such as companies, contacts, tickets, projects, billing items, time entries, notes, and attachments, with CRUD capabilities and advanced search. The server also includes id-to-name resolution, smart caching for performance, and supports both local stdio transport and HTTP streamable transport for remote deployments. To use it, configure credentials and transport, then run the server so that your MCP client (e.g., Claude Desktop or Claude Code) can connect to the MCP endpoint and issue MCP requests to manage Autotask data via the provided tools.
How to install
- Prerequisites:
- Node.js 18+ installed on your machine
- npm (comes with Node.js) or pnpm
- Autotask API credentials (username/email, secret, integration code)
- Access to the MCP client you plan to use (Claude Desktop/Claude Code or compatible MCP client)
- Clone the repository and install dependencies:
git clone https://github.com/wyre-technology/autotask-mcp.git
cd autotask-mcp
npm ci
- Build the project (if you are running from source):
npm run build
- Run or configure the MCP server using the Node.js entry (example config shown in mcp_config):
{
"mcpServers": {
"autotask": {
"command": "node",
"args": ["/path/to/autotask-mcp/dist/entry.js"],
"env": {
"AUTOTASK_USERNAME": "your-user@company.com",
"AUTOTASK_SECRET": "your-secret",
"AUTOTASK_INTEGRATION_CODE": "your-code"
}
}
}
}
- Alternative deployment (Docker): follow the README’s Docker options to run in stdio or HTTP transports, if you prefer containerized deployment. Ensure you supply the same AUTOTASK_* environment variables when starting the container.
Additional notes
- The server supports multiple transport modes: stdio for local desktop usage and HTTP streamable transport for remote deployments behind a gateway or in Docker.
- In gateway mode, credentials can be injected by a gateway, so you may set AUTH_MODE=gateway and MCP_TRANSPORT=http, with credentials passed via HTTP headers.
- Ensure MCP client configuration points at the correct transport endpoint (e.g., dist/entry.js for node-based from-source setup, or the HTTP endpoint when using Docker).
- Use the provided environment variables to keep credentials out of your codebase; consider using a secrets manager in production.
- If you experience connection or authentication issues, verify that AUTOTASK_API_URL (if overridden) is reachable and that the Autotask credentials are valid.
- The server exposes 39+ tools and comprehensive API coverage; consult the API Reference section in the README for details on specific resources and operations.
Related MCP Servers
mcp -text-editor
An open source implementation of the Claude built-in text editor tool
docmole
Dig through any documentation with AI - MCP server for Claude, Cursor, and other AI assistants
obsidian
MCP server for Obsidian vault management - enables Claude and other AI assistants to read, write, search, and organize your notes
gmail
A robust Model Context Protocol server for Gmail integration with intelligent authentication and comprehensive email operations
mcp-tidy
CLI tool to visualize and manage MCP server configurations in Claude Code. List servers, analyze usage statistics, and clean up unused servers
harvest
MCP server for Harvest time tracking API - use with Claude Desktop and other AI assistants