Tability MCP Server
Enables AI assistants to manage OKRs, track goals, and update progress on the Tability platform using natural language. It provides 27 tools for interacting with plans, objectives, outcomes, initiatives, and workspace memberships via the Tability API.
README
Tability MCP Server
A Model Context Protocol (MCP) server for Tability.app - the OKR and goal tracking platform.
This MCP server enables AI assistants like Claude to interact with your Tability workspace, allowing you to manage OKRs, track progress, and update checkins through natural language.
Features
This MCP server provides 27 tools covering all Tability API endpoints:
User & Workspace
tability_whoami- Get authenticated user profiletability_get_workspace- Get workspace details
Memberships (Team Management)
tability_list_memberships- List all workspace members with filteringtability_get_membership- Get specific member detailstability_get_membership_manager- Get a member's managertability_get_membership_direct_reports- Get direct reportstability_update_membership- Update member role or managertability_delete_membership- Remove a membertability_add_memberships- Invite new userstability_add_readonly_memberships- Add read-only users (free tier)
Plans
tability_list_plans- List all plans with paginationtability_get_plan- Get specific plan details
Objectives
tability_list_objectives_for_plan- Get objectives in a plantability_get_objective- Get specific objective details
Outcomes (Key Results)
tability_list_outcomes_for_plan- Get outcomes in a plantability_list_outcomes_for_objective- Get outcomes for an objectivetability_get_outcome- Get specific outcome details
Initiatives
tability_list_initiatives_for_plan- Get initiatives in a plantability_list_initiatives_for_outcome- Get initiatives for an outcometability_get_initiative- Get specific initiative details
Checkins (Progress Updates)
tability_list_checkins_for_outcome- Get checkin historytability_get_checkin- Get specific checkin detailstability_create_checkin- Create a new progress update
Search
tability_search_plans- Search plans with filterstability_search_objectives- Search objectives with filterstability_search_outcomes- Search outcomes with filterstability_search_initiatives- Search initiatives with filters
Installation
Prerequisites
- Node.js 18 or higher
- A Tability account with API access enabled
Getting Your API Token
- Log into Tability
- Go to your Account details
- Copy your Personal API token
- Ensure "API access" is enabled in each workspace you want to use
Install from Source
# Clone the repository
git clone https://github.com/luquimbo/tability-mcp.git
cd tability-mcp
# Install dependencies
npm install
# Build the project
npm run build
Configuration
For 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
{
"mcpServers": {
"tability": {
"command": "node",
"args": ["/absolute/path/to/tability-mcp/dist/index.js"],
"env": {
"TABILITY_API_TOKEN": "your-api-token-here"
}
}
}
}
For Claude Code
Add to your project's .mcp.json:
{
"mcpServers": {
"tability": {
"command": "node",
"args": ["./dist/index.js"],
"cwd": "/path/to/tability-mcp",
"env": {
"TABILITY_API_TOKEN": "your-api-token-here"
}
}
}
}
Environment Variables
| Variable | Required | Description |
|---|---|---|
TABILITY_API_TOKEN |
Yes | Your Tability Personal API token |
Usage Examples
Once configured, you can interact with Tability through Claude:
Get current user info:
"Who am I in Tability?"
List all plans:
"Show me all OKR plans in my workspace 'acme'"
Check progress on a plan:
"What's the progress on the Q1 2024 OKRs?"
Create a checkin:
"Update the 'Revenue' outcome to 150000 with confidence green and note 'Great month!'"
Search for initiatives:
"Find all active initiatives in progress"
Development
# Run in development mode with hot reload
npm run dev
# Build for production
npm run build
# Test with MCP Inspector
npm run inspector
API Documentation
This MCP server implements the Tability API v2.
Key concepts:
- Plans: Time-bound collections of objectives (e.g., "Q1 2024 OKRs")
- Objectives: High-level goals within a plan
- Outcomes: Measurable key results under each objective
- Initiatives: Actions/projects linked to outcomes
- Checkins: Progress updates with score, confidence, and notes
Security Notes
- Keep your API token secure - never commit it to version control
- The API token has the same access level as your Tability user
- API access must be enabled per-workspace in Tability settings
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。