Lattice HQ MCP Server

Lattice HQ MCP Server

Enables AI models to interact with the Lattice HQ performance management platform for managing users, goals, review cycles, feedback, departments, and updates.

Category
访问服务器

README

Lattice HQ MCP Server

A Model Context Protocol (MCP) server for Lattice HQ that enables AI models to interact with your Lattice performance management platform.

Features

This MCP server provides access to the following Lattice HQ capabilities:

User Management

  • Get all users in the organization
  • Get specific user details
  • Get direct reports for any user
  • Get current user information

Goal Management

  • Get all goals in the organization
  • Get specific goal details
  • Get goals for a specific user

Review Cycles

  • Get all review cycles
  • Get specific review cycle details
  • Get reviewees for a review cycle

Feedback

  • Get all feedback
  • Get specific feedback details

Departments

  • Get all departments
  • Get specific department details

Updates

  • Get all updates
  • Get specific update details

Prerequisites

  • Node.js 18 or higher
  • Lattice HQ account with API access
  • Lattice API token

Installation

Method 1: Using NPX (Recommended)

No installation required! Just use npx to run the latest version:

LATTICE_API_URL=https://your-company.latticehq.com npx lattice-hq-mcp-server --api-key=YOUR-TOKEN --stdio

Method 2: Global Installation

# Install globally
npm install -g lattice-hq-mcp-server

# Run the server
LATTICE_API_URL=https://your-company.latticehq.com lattice-hq-mcp-server --api-key=YOUR-TOKEN --stdio

Method 3: Local Development

# Clone the repository
git clone https://github.com/cyrilnoah1/lattice-hq-mcp.git
cd lattice-hq-mcp

# Install dependencies
npm install

# Build the project
npm run build

# Run the server
npm run dev

Getting Your Lattice API Token

Method 1: Through Lattice Settings

  1. Log in to your Lattice HQ account
  2. Go to Settings → Integrations → API (if available)
  3. Generate a new API token
  4. Copy the token and add it to your configuration

Method 2: Contact Lattice Support

If you don't see "Integrations" under Settings, this usually means:

  • Your plan doesn't include API access (typically Enterprise only)
  • You don't have admin permissions
  • API access needs to be enabled for your account

Contact Lattice Support:

  • Email: support@lattice.com
  • Request API access for your account/plan

Usage

Running the Server

With API Token:

export LATTICE_API_TOKEN=your_token_here
export LATTICE_API_URL=https://your-company.latticehq.com
lattice-hq-mcp-server --stdio

Or inline:

LATTICE_API_URL=https://your-company.latticehq.com lattice-hq-mcp-server --api-key=your_token_here --stdio

Using with Claude Desktop

Add the following to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

Configuration:

{
  "mcpServers": {
    "lattice-hq": {
      "command": "npx",
      "args": ["-y", "lattice-hq-mcp-server", "--api-key=YOUR-TOKEN", "--stdio"],
      "env": {
        "LATTICE_API_URL": "https://your-company.latticehq.com"
      }
    }
  }
}

Configuration:

{
  "mcpServers": {
    "lattice-hq": {
      "command": "node",
      "args": ["/path/to/lattice-hq-mcp/dist/index.js"],
      "env": {
        "LATTICE_API_URL": "https://your-company.latticehq.com",
        "LATTICE_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

Using with Other MCP Clients

This server follows the standard MCP protocol and can be used with any MCP-compatible client.

Available Tools

User Tools

  • lattice_get_users - Get all users
  • lattice_get_user - Get user by ID
  • lattice_get_user_direct_reports - Get user's direct reports
  • lattice_get_me - Get current user

Goal Tools

  • lattice_get_goals - Get all goals
  • lattice_get_goal - Get goal by ID
  • lattice_get_user_goals - Get goals for a user

Review Cycle Tools

  • lattice_get_review_cycles - Get all review cycles
  • lattice_get_review_cycle - Get review cycle by ID
  • lattice_get_review_cycle_reviewees - Get reviewees for a cycle

Feedback Tools

  • lattice_get_feedbacks - Get all feedback
  • lattice_get_feedback - Get feedback by ID

Department Tools

  • lattice_get_departments - Get all departments
  • lattice_get_department - Get department by ID

Update Tools

  • lattice_get_updates - Get all updates
  • lattice_get_update - Get update by ID

Configuration

You can configure the server using environment variables:

  • LATTICE_API_TOKEN: Your Lattice API token (required)
  • LATTICE_API_URL: Lattice API base URL (required)

Development

# Install dependencies
npm install

# Build in watch mode
npm run watch

# Run development server
npm run dev

# Build for production
npm run build

Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

If you encounter any issues:

  1. Check the GitHub Issues
  2. Create a new issue with details about your problem
  3. Include your Node.js version, operating system, and any error messages

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选