Freelo MCP Server
Integrates with Freelo project management API to retrieve task details, list subtasks with completion status, and download files from task comments.
README
freelo-mcp
A Model Context Protocol (MCP) server built with mcp-framework that provides integration with Freelo project management API.
Features
This MCP server exposes tools for interacting with Freelo tasks, subtasks, and files:
- freelo_get_task - Get detailed information about a task including comments and attached files
- freelo_list_task_subtasks - List all subtasks with completion status
- freelo_download_file - Download files from task comments using UUID
Quick Start
1. Get Your Freelo API Key
- Log in to your Freelo Dashboard
- Click on your avatar in the top right corner → Settings
- Scroll to the bottom to find your API Key
2. Add to Claude Code
claude mcp add freelo-mcp -e FREELO_EMAIL=your-email@example.com -e FREELO_API_KEY=your-api-key -- npx -y @liquiddesign/freelo-mcp
That's it! You can now use Freelo tools in Claude Code.
Alternative Setup
Claude Code (Manual)
Add to your MCP settings (~/.claude/settings.json or project .mcp.json):
{
"mcpServers": {
"freelo-mcp": {
"command": "npx",
"args": ["-y", "@liquiddesign/freelo-mcp"],
"env": {
"FREELO_EMAIL": "your-email@example.com",
"FREELO_API_KEY": "your-api-key-here"
}
}
}
}
Claude Desktop
Add to Claude Desktop configuration file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"freelo-mcp": {
"command": "npx",
"args": ["-y", "@liquiddesign/freelo-mcp"],
"env": {
"FREELO_EMAIL": "your-email@example.com",
"FREELO_API_KEY": "your-api-key-here"
}
}
}
}
Development
# Install dependencies
npm install
# Build the project
npm run build
# Watch mode during development
npm run watch
For local development, configure Claude to use the built project directly:
{
"mcpServers": {
"freelo-mcp": {
"command": "node",
"args": ["/absolute/path/to/freelo-mcp/dist/index.js"],
"env": {
"FREELO_EMAIL": "your-email@example.com",
"FREELO_API_KEY": "your-api-key-here"
}
}
}
}
Project Structure
freelo-mcp/
├── src/
│ ├── tools/ # MCP Tools
│ │ ├── FreeloGetTask.ts # Get task details with comments & files
│ │ ├── FreeloListTaskSubtasks.ts # List task subtasks
│ │ └── FreeloDownloadFile.ts # Download files by UUID
│ ├── utils/
│ │ └── freeloApi.ts # Freelo API client & types
│ └── index.ts # Server entry point
├── package.json
├── tsconfig.json
└── CLAUDE.md # Claude Code instructions
Available Tools
1. freelo_get_task
Get detailed information about a specific Freelo task, including all comments and attached files.
Parameters:
taskId(number) - The unique ID of the task
Returns:
- Task name, description, priority, state
- Author and assignee information
- Dates (created, due, completed)
- Project and task list details
- Tags and time estimates
- Comments with content, author, timestamps, and attached files (with UUIDs)
Example:
Use freelo_get_task with taskId: 12345
2. freelo_list_task_subtasks
List all subtasks of a specific task with completion statistics.
Parameters:
taskId(number) - The unique ID of the task
Returns:
- Array of subtasks with names, state, dates, author, assignee
- Statistics (total, completed, remaining, completion percentage)
Example:
Use freelo_list_task_subtasks with taskId: 12345
3. freelo_download_file
Download a file from Freelo using its UUID. File UUIDs are found in task comments (use freelo_get_task first).
Parameters:
fileUuid(string) - The UUID of the file (from task comments)filename(string, optional) - Custom filename to save as
Returns:
- Downloaded file path (in system temp directory)
- File metadata (UUID, filename, size)
Example:
Use freelo_download_file with fileUuid: "550e8400-e29b-41d4-a716-446655440000"
Adding New Tools
You can extend this MCP server with additional Freelo API tools:
# Add a new tool using mcp-framework CLI
mcp add tool my-tool
# Examples of additional Freelo tools you might create:
# - freelo_list_projects
# - freelo_create_task
# - freelo_add_comment
Tool Development
Example tool structure:
import { MCPTool } from "mcp-framework";
import { z } from "zod";
interface MyToolInput {
message: string;
}
class MyTool extends MCPTool<MyToolInput> {
name = "my_tool";
description = "Describes what your tool does";
schema = {
message: {
type: z.string(),
description: "Description of this input parameter",
},
};
async execute(input: MyToolInput) {
// Your tool logic here
return `Processed: ${input.message}`;
}
}
export default MyTool;
Publishing to npm
-
Update your package.json:
- Ensure
nameis unique and follows npm naming conventions - Set appropriate
version - Add
description,author,license, etc. - Check
binpoints to the correct entry file
- Ensure
-
Build and test locally:
npm run build npm link freelo-mcp # Test your CLI locally -
Login to npm (create account if necessary):
npm login -
Publish your package:
npm publish
After publishing, users can add it to their Claude Desktop client (see below) or run it with npx.
Usage with Claude Desktop
After building the project and configuring your credentials (see Freelo API Setup), restart Claude Desktop to load the MCP server.
You can then use the Freelo tools in your conversations with Claude:
Example conversation:
You: "Get details for Freelo task 12345"
Claude: [Uses freelo_get_task tool and returns task info with comments and files]
You: "Show me the subtasks"
Claude: [Uses freelo_list_task_subtasks tool and displays subtasks]
You: "Download the first file attachment"
Claude: [Uses freelo_download_file with the UUID from the task comments]
Building and Testing
- Make changes to your tools
- Run
npm run buildto compile - The server will automatically load your tools on startup
Learn More
MCP Framework
Freelo API
- Freelo API Documentation - Official API reference
- Freelo API Help - How to get your API key
- Freelo Website - Project management platform
API Reference
This MCP server uses the Freelo REST API v1:
- Base URL:
https://api.freelo.io/v1 - Authentication: HTTP Basic Auth (email:apiKey)
- Response Format: JSON
- Current Support: Read-only operations (GET endpoints)
For detailed API specifications, see the official Freelo API documentation.
Contributing
This is a personal project for Freelo API integration. Feel free to extend it with additional tools or improvements.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。