@purinton/tasklit-mcp

Tasklit MCP is a Model Context Protocol (MCP) server providing a set of custom tools for AI and automation workflows, focused on task management. It is designed for integration with AI agents and automation clients, and is easily extendable with your own tools.

---

Table of Contents

• Overview
• Features
• Available Tools
• Usage
• Extending & Customizing
• Support
• License
• Links

Overview

This project is an MCP server built on @purinton/mcp-server . It exposes a set of tools via the Model Context Protocol, making them accessible to AI agents and automation clients.

Features

• Dynamic tool loading from the tools/ directory
• Task management tools: create, update, delete, search, get, and log time on tasks
• Simple to add or modify tools
• HTTP API with authentication
• Built for easy extension
• Ready for Docker and systemd deployment

Available Tools

Below is a list of tools provided by this MCP server. Each tool can be called via the MCP protocol or HTTP API.

task-create

Description: Creates one or more tasks. Returns an array of the task IDs that were created.

Input Schema:

1{
2  "tasks": [
3    {
4      "details": "string (optional)",
5      "parent_id": "number (optional)",
6      "scheduled_time": "string (optional)",
7      "sort_order": "number (optional)",
8      "status": "pending | in progress | on hold | blocked | review | cancelled | completed (optional)",
9      "title": "string"
10    }
11  ]
12}

Example Request:

1{
2  "tool": "task-create",
3  "args": {
4    "tasks": [
5      { "title": "Write documentation", "status": "pending" }
6    ]
7  }
8}

Example Response:

1{
2  "message": "task-create-reply",
3  "data": { "task_ids": [123] }
4}

task-update

Description: Updates one or more tasks by ID.

Input Schema:

1{
2  "tasks": [
3    {
4      "id": "number",
5      "details": "string (optional)",
6      "parent_id": "number (optional)",
7      "scheduled_time": "string (optional)",
8      "sort_order": "number (optional)",
9      "status": "pending | in progress | on hold | blocked | review | cancelled | completed (optional)",
10      "time_logged": "number (optional)",
11      "title": "string (optional)"
12    }
13  ]
14}

Example Request:

1{
2  "tool": "task-update",
3  "args": {
4    "tasks": [
5      { "id": 123, "status": "completed" }
6    ]
7  }
8}

Example Response:

1{
2  "message": "task-update-reply",
3  "data": { "success": true }
4}

task-delete

Description: Delete one or more tasks by their IDs.

Input Schema:

1{
2  "task_ids": [123, 124]
3}

Example Request:

1{
2  "tool": "task-delete",
3  "args": { "task_ids": [123] }
4}

Example Response:

1{
2  "message": "task-delete-reply",
3  "data": { "deleted": [123] }
4}

task-get

Description: Get all of a task's info by its ID.

Input Schema:

1{
2  "task_ids": [123]
3}

Example Request:

1{
2  "tool": "task-get",
3  "args": { "task_ids": [123] }
4}

Example Response:

1{
2  "message": "task-get-reply",
3  "data": { "tasks": [ { "id": 123, "title": "Write documentation", ... } ] }
4}

task-search

Description: Search/list all task titles and details for given statuses.

Input Schema:

1{
2  "search_string": "string (optional)",
3  "includes": {
4    "pending": true,
5    "in progress": true,
6    "on hold": false,
7    "blocked": false,
8    "review": false,
9    "cancelled": false,
10    "completed": false
11  }
12}

Example Request:

1{
2  "tool": "task-search",
3  "args": {
4    "search_string": "documentation",
5    "includes": { "pending": true, "in progress": true, "on hold": false, "blocked": false, "review": false, "cancelled": false, "completed": false }
6  }
7}

Example Response:

1{
2  "message": "task-search-reply",
3  "data": { "tasks": [ { "id": 123, "title": "Write documentation" } ] }
4}

task-log-time

Description: Add or remove time spent on a task.

Input Schema:

1{
2  "tasks": [
3    { "task_id": 123, "minutes": 30 }
4  ]
5}

Example Request:

1{
2  "tool": "task-log-time",
3  "args": { "tasks": [ { "task_id": 123, "minutes": 30 } ] }
4}

Example Response:

1{
2  "message": "task-log-time-reply",
3  "data": { "success": true }
4}

Usage

1. Install dependencies:

   1npm install

2. Configure environment variables:

   • MCP_PORT: (optional) Port to run the server (default: 1234)
   • MCP_TOKEN: (optional) Bearer token for authentication

3. Start the server:

   1node tasklit-mcp.mjs

4. Call tools via HTTP or MCP client.
   See the @purinton/mcp-server documentation for protocol/API details.

Extending & Customizing

To add a new tool:

1. Create a new file in the tools/ directory (e.g., tools/mytool.mjs):

1import { z, buildResponse } from '@purinton/mcp-server';
2export default async function ({ mcpServer, toolName, log }) {
3  mcpServer.tool(
4    toolName,
5    "Write a brief description of your tool here",
6    { echoText: z.string() },
7    async (_args,_extra) => {
8      log.debug(`${toolName} Request`, { _args });
9      const response = 'Hello World!';
10      log.debug(`${toolName} Response`, { response });
11      return buildResponse(response);
12    }
13  );
14}

1. Document your tool in the Available Tools section above.
2. Restart the server to load new tools.

You can add as many tools as you like. Each tool is a self-contained module.

Running as a systemd Service

You can run this server as a background service on Linux using the provided tasklit-mcp.service file.

1. Copy the service file

Copy tasklit-mcp.service to your systemd directory (usually /etc/systemd/system/):

1sudo cp tasklit-mcp.service /usr/lib/systemd/system/

2. Adjust paths and environment

• Make sure the WorkingDirectory and ExecStart paths in the service file match where your project is installed (default: /opt/tasklit-mcp).
• Ensure your environment file exists at /opt/tasklit-mcp/.env if you use one.

3. Reload systemd and enable the service

1sudo systemctl daemon-reload
2sudo systemctl enable tasklit-mcp
3sudo systemctl start tasklit-mcp

4. Check service status

1sudo systemctl status tasklit-mcp

The server will now run in the background and restart automatically on failure or reboot.

Running with Docker

You can run this MCP server in a Docker container using the provided Dockerfile.

1. Build the Docker image

1docker build -t tasklit-mcp .

2. Run the container

Set your environment variables (such as MCP_TOKEN) and map the port as needed:

1docker run -d \
2  -e MCP_TOKEN=your_secret_token \
3  -e MCP_PORT=1234 \
4  -p 1234:1234 \
5  --name tasklit-mcp \
6  tasklit-mcp

• Replace your_secret_token with your desired token.
• You can override the port by changing -e MCP_PORT and -p values.

3. Updating the image

If you make changes to the code, rebuild the image and restart the container:

1docker build -t tasklit-mcp .
2docker stop tasklit-mcp && docker rm tasklit-mcp
3# Then run the container again as above

---

Support

For help, questions, or to chat with the author and community, visit:

Purinton Dev on Discord

License

MIT © 2025 Russell Purinton

Links

• @purinton/mcp-server on npm
• GitHub Repo
• GitHub Org
• GitHub Personal
• Discord