kazkozdev-abscissaSAFE
A safety-aware MCP server that lets AI agents manage Linear issues, projects, cycles, and dependencies.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
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
dc8810d05811OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add abscissa --env LINEAR_API_KEY=${LINEAR_API_KEY} -- None abscissa==0.1.3Exposed tools (17)
17 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_current_user | read | Return the authenticated Linear user behind the configured API key. |
get_issue | read | Get full issue details, including comments, labels, assignee, and dates. |
get_project | read | Get a project by UUID. |
get_team | read | Get a team by key (for example, ART) or UUID. |
get_user_issues | read | Get a user |
list_cycle_issues | read | List issues in a cycle. Pass next_cursor as cursor for the next page. |
list_cycles | read | List workspace cycles, optionally filtered by a team key or UUID. |
list_issue_dependencies | read | List issues this issue blocks and issues that block it. |
list_issue_labels | read | List labels for a team. Pass next_cursor as cursor for the next page. |
list_project_issues | read | List a project |
list_project_labels | read | List reusable project labels. Pass next_cursor as cursor for the next page. |
list_project_updates | read | List a project |
list_projects | read | List projects. Pass next_cursor as cursor for the next page. |
list_teams | read | List teams. Pass next_cursor as cursor for the next page. |
list_users | read | List organization users. Pass next_cursor as cursor for the next page. |
list_workflow_states | read | List workflow states for a team. Pass next_cursor as cursor for the next page. |
search_issues | read | Search Linear issues with filters. Pass next_cursor as cursor for the next page. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
docs/assets/banner.png
not replace Linear's own access controls: the API key still determines which
Gates applied: no_behavioural_pass.
dc8810d05811full audit observations/trust-audit/mcp-server/kazkozdev__abscissa.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | dc8810d05811 | SAFE | B | 89 | first audit |
Questions
What is the kazkozdev-abscissa MCP server?
A safety-aware MCP server that lets AI agents manage Linear issues, projects, cycles, and dependencies.
What tools does kazkozdev-abscissa expose?
17 in total: 17 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is kazkozdev-abscissa safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does kazkozdev-abscissa need?
It reads LINEAR_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does kazkozdev-abscissa run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as abscissa.
How current is this page?
The grade is for one exact copy of the source (dc8810d05811), read on 2026-10-11. The repository is watched and re-audited when it changes.