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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.