mcpField
A
Abscissa

Abscissa

Local
github.comProductivity1Updated 16w ago

About Abscissa

Abscissa is a local Python MCP server for managing Linear workspaces through an MCP client. It covers issues, projects, cycles, and dependencies, with cursor pagination and explicit confirmation for destructive actions.

Key features

  1. 01Manage Linear issues, projects, and cycles
  2. 02Create and inspect issue dependencies
  3. 03Work with comments, labels, teams, and users
  4. 04Paginate list and search results
  5. 05Require confirmation for archive and delete actions

Use cases

  1. 01Review and group assigned open issues
  2. 02Create or update issues and project records
  3. 03Inspect issues blocked by another issue

MCP support

Abscissa exposes 42 Linear tools through the MCP stdio transport for compatible clients. It reads the Linear API key from its process environment.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"abscissa": {
"command": "uvx",
"args": [
"abscissa"
],
"env": {
"LINEAR_API_KEY": "<LINEAR_API_KEY>"
}
}
}
}
Run commanduvx abscissa
Environment variables to set
LINEAR_API_KEYSecretLinear personal API key used to authenticate API requests.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiabscissa0.1.3

Tools

42

Saved tool list · updated 3w ago

This tool takes no parameters.

Details

From the project README

Abscissa

Abscissa is a Python stdio MCP server for Linear. It turns Linear's GraphQL API into 42 tools for an MCP client: issues, projects, cycles, dependencies, comments, labels, workflow states, teams, and users.

The design priority is deliberate control over project data. Read operations return cursor-paginated results; get_user_issues() resolves the authenticated Linear user; archive and delete tools require an explicit confirm=true before they make a destructive API call. The server stores no credentials and reads LINEAR_API_KEY from its process environment.

Abscissa uses the stdio transport from the Model Context Protocol. Any client that supports stdio MCP can launch it as a local tool process.

Run it

You need Python 3.10+ and a Linear personal API key.

git clone https://github.com/KazKozDev/abscissa.git
cd abscissa
python3 -m venv .venv
.venv/bin/pip install -e '.[dev]'
export LINEAR_API_KEY='lin_api_…'
.venv/bin/abscissa

You can also install Abscissa directly from PyPI:

pip install abscissa

The final command starts the MCP server on standard input and output. Register .venv/bin/abscissa as a stdio command in your MCP client, and pass LINEAR_API_KEY through that client's environment or secret manager.

The key remains outside the repository. The .gitignore excludes common local environment files, including .env and .venv.

Example prompts

Once Abscissa is registered in your MCP client, try prompts like:

Show my open Linear issues grouped by project.
Create an issue in ENG for fixing onboarding copy.
List issues blocked by GEN-32.

Tools

AreaTools
Identityget_current_user
Issuescreate_issue, update_issue, search_issues, get_user_issues, get_issue, assign_issue, add_comment, set_issue_estimate
Issue lifecyclearchive_issue, delete_issue
Dependencieslist_issue_dependencies, add_issue_dependency, remove_issue_dependency
Labels and workflowlist_workflow_states, list_issue_labels, create_label, add_issue_label, remove_issue_label
Teams and peoplelist_teams, get_team, list_users
Projectscreate_project, get_project, list_projects, list_project_issues, set_issue_project, remove_issue_from_project, update_project, update_project_details, archive_project
Project labelslist_project_labels, create_project_label, add_project_label, remove_project_label
Project updatescreate_project_update, list_project_updates
Cyclescreate_cycle, update_cycle, archive_cycle, list_cycles, list_cycle_issues

Search and list tools accept limit and cursor. Their responses keep the same shape:

{
  "items": [],
  "next_cursor": null
}

Pass a non-null next_cursor back as cursor to request the next page.

list_issue_dependencies returns separate blocks and blocked_by lists. Each item includes its relation_id; use it to remove that dependency. Its next_cursors object has separate cursors for each direction.

Destructive actions

archive_issue, archive_project, and delete_issue are marked with MCP's destructiveHint. They refuse to call Linear until the client invokes them with confirm=true.

Deletion requires explicit confirmation: set confirm=true

This prevents an accidental tool call from deleting or archiving data. It does not replace Linear's own access controls: the API key still determines which resources the server may read or change.

Verify the checkout

.venv/bin/ruff check .
.venv/bin/python -m pytest

The current checkout produces:

All checks passed!
..........                                                               [100%]
10 passed

The tests cover pagination bounds and response shape, authenticated-user issue resolution, project membership, cycle queries, dependency direction, confirmation guards, cycle lifecycle operations, and MCP tool registration. GitHub Actions runs the same lint and test commands on Python 3.10, 3.11, 3.12, and 3.13.

Limitations

Abscissa is a local stdio server, not an HTTP service. It needs a running MCP-capable client and a valid Linear API key. The automated suite avoids mutating a real Linear workspace; create, update, archive, and delete behavior is therefore protected by unit tests rather than a live write test.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.