Lattice MCP Server
An MCP server that exposes the Lattice Talent API as tools, enabling AI assistants like Claude to read and manage people data, goals, feedback, reviews, and more.
README
Lattice MCP Server
An MCP (Model Context Protocol) server that exposes the Lattice Talent API as tools — so AI assistants like Claude can read and manage your people data, goals, feedback, reviews, and more.
Prerequisites
- Node.js 18+
- A Lattice API key (generate one from your Lattice admin dashboard under Integrations → API)
Quick Start
1. Clone & install
git clone https://github.com/EoinFalconer/lattice-mcp.git
cd lattice-mcp
npm install
2. Build
npm run build
3. Configure your MCP client
Add the server to your MCP client configuration. For example, in Claude Code (~/.claude/settings.json or project-level .mcp.json):
{
"mcpServers": {
"lattice": {
"command": "node",
"args": ["/absolute/path/to/lattice-mcp/dist/index.js"],
"env": {
"LATTICE_API_KEY": "your-api-key-here"
}
}
}
}
For EMEA data residency, add "LATTICE_REGION": "emea" to the env block.
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
LATTICE_API_KEY |
Yes | — | Your Lattice API key |
LATTICE_REGION |
No | us |
Data residency region: us or emea |
Available Tools (30)
Users
| Tool | Description |
|---|---|
get_current_user |
Get the authenticated user |
get_user |
Get a user by ID |
list_users |
List all users (paginated) |
get_user_direct_reports |
Get a user's direct reports |
get_user_custom_attributes |
Get custom attributes for a user |
get_user_goals |
Get goals for a user |
get_user_tasks |
Get tasks for a user |
Goals
| Tool | Description |
|---|---|
get_goal |
Get a goal by ID |
list_goals |
List goals, optionally filtered by state |
create_goal |
Create a new goal |
update_goal |
Update an existing goal (full PUT) |
Goal Updates
| Tool | Description |
|---|---|
create_goal_update |
Add a progress update to a goal |
get_goal_updates |
Get updates for a specific goal |
list_all_goal_updates |
Get all goal updates across goals |
Departments
| Tool | Description |
|---|---|
get_department |
Get a department by ID |
list_departments |
List all departments |
Feedback
| Tool | Description |
|---|---|
get_feedback |
Get a feedback entry by ID |
list_feedback |
List all continuous feedback |
Review Cycles
| Tool | Description |
|---|---|
get_review_cycle |
Get a review cycle by ID |
list_review_cycles |
List all review cycles |
get_review_cycle_reviewees |
Get reviewees for a cycle |
get_review_cycle_reviews |
Get reviews for a cycle |
Reviewees
| Tool | Description |
|---|---|
get_reviewee |
Get a reviewee by ID |
get_reviewee_reviews |
Get reviews for a reviewee |
Questions
| Tool | Description |
|---|---|
get_question |
Get a review question by ID |
get_question_revision |
Get a question revision by ID |
Other
| Tool | Description |
|---|---|
get_competency |
Get a competency by ID |
get_custom_attribute |
Get a custom attribute definition |
get_custom_attribute_value |
Get a custom attribute value |
get_tag / list_tags |
Get or list tags |
get_update / list_updates |
Get or list updates |
get_task |
Get a task by ID |
API Notes
- Pagination — Cursor-based. Use
limit(1–100) andstartingAfter(theendingCursorfrom the previous response). - Rate limits — 240 requests/minute. 429 responses include a
Retry-Afterheader. - Base URLs — US:
api.latticehq.com/ EMEA:api.emea.latticehq.com
License
ISC
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。