Abscissa
About
A safety-aware MCP server that lets AI agents manage Linear issues, projects, cycles, and dependencies.
Details
- Author
- KazKozDev
- GitHub stars
- 1
- Downloads
- 303
- Categories
- Productivity, Project Management, AI
Jump to
- 35 tools for Linear issues, projects, cycles, labels, workflow states, teams, users, comments, and dependencies.
- Cursor pagination for list and search operations.
- Current-user resolution through get_current_user and get_user_issues.
- Issue dependency tools for blocked and blocking relationships.
- Explicit confirm=true protection for destructive archive and delete actions.
- Published on PyPI and the official MCP Registry.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AbscissaCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install Abscissa from PyPI:
pip install abscissa
Create a Linear personal API key, then register Abscissa as a stdio MCP server in your MCP-compatible client.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"abscissa": {
"abscissa": {
"command": "abscissa",
"args": [],
"env": {
"LINEAR_API_KEY": "lin_api_..."
}
}
}
}
}McpServers
{
"abscissa": {
"command": "abscissa",
"args": [],
"env": {
"LINEAR_API_KEY": "lin_api_..."
}
}
}Abscissa is a safety-aware stdio MCP server for Linear. It gives MCP-compatible AI clients 35 tools for working with Linear issues, projects, cycles, comments, labels, workflow states, users, and dependencies.
It is designed for controlled access to project data: list and search tools support cursor pagination, user-specific issue queries resolve the authenticated Linear user, and destructive archive/delete tools require an explicit confirm=true argument before calling Linear.
Abscissa runs locally, stores no credentials, and reads LINEAR_API_KEY from the process environment. It is published on PyPI and the official MCP Registry.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
