LinearSAFE
A server that integrates Linear's project management system with the Model Context Protocol (MCP) to allow LLMs to interact with Linear.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/linear-mcp-server) [](https://smithery.ai/server/linear-mcp-server)
IMPORTANT NOTE: This MCP Server is now deprecated and is no longer being maintained. I recommend you use the official Linear remote MCP server here: https://linear.app/changelog/2025-05-01-mcp (https://mcp.linear.app/sse)
A Model Context Protocol server for the Linear API.
This server provides integration with Linear's issue tracking system through MCP, allowing LLMs to interact with Linear issues.
Installation
Automatic Installation
To install the Linear MCP server for Claude Desktop automatically via Smithery:
npx @smithery/cli install linear-mcp-server --client claude
Manual Installation
- Create or get a Linear API key for your team: https://linear.app/YOUR-TEAM/settings/api
- Add server config to Claude Desktop:
- MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"linear": {
"command": "npx",
"args": [
"-y",
"linear-mcp-server"
],
"env": {
"LINEAR_API_KEY": "your_linear_api_key_here"
}
}
}
}Components
Tools
- `linear_create_issue`: Create a new Linear issues
- Required inputs:
title(string): Issue titleteamId(string): Team ID to create issue in- Optional inputs:
description(string): Issue description (markdown supported)priority(number, 0-4): Priority level (1=urgent, 4=low)status(string): Initial status name
- `linear_update_issue`: Update existing issues
- Requir
34c231a0ed74OBSERVED · 2026-10-02Connect
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 linear-mcp-server --env LINEAR_API_KEY=${LINEAR_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"linear-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"LINEAR_API_KEY": "${LINEAR_API_KEY}"
}
}
}
}Exposed tools (6)
3 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
linear-server-prompt | read | Instructions for using the Linear MCP server effectively |
linear_add_comment | write | Adds a comment to an existing Linear issue. Supports markdown formatting in the comment body. Can optionally specify a custom user name and avatar for the comment. Returns the created comment |
linear_create_issue | write | Creates a new Linear issue with specified details. Use this to create tickets for tasks, bugs, or feature requests. Returns the created issue |
linear_get_user_issues | read | Retrieves issues assigned to a specific user or the authenticated user if no userId is provided. Returns issues sorted by last updated, including priority, status, and other metadata. Useful for finding a user |
linear_search_issues | read | Searches Linear issues using flexible criteria. Supports filtering by any combination of: title/description text, team, status, assignee, labels, priority (1=urgent, 2=high, 3=normal, 4=low), and estimate. Returns up to 10 issues by default (configurable via limit). |
linear_update_issue | write | Updates an existing Linear issue |
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
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@linear/sdk, @modelcontextprotocol/sdk, dotenv, zod, @types/node, typescript
Gates applied: no_behavioural_pass.
34c231a0ed74full audit observations/trust-audit/mcp-server/jerhadf__linear.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 |
|---|---|---|---|---|---|
| 2026-10-02 | 34c231a0ed74 | SAFE | B | 89 | first audit |
Questions
What is the Linear MCP server?
A server that integrates Linear's project management system with the Model Context Protocol (MCP) to allow LLMs to interact with Linear.
What tools does Linear expose?
6 in total: 3 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Linear 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 Linear 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 Linear run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as linear-mcp-server at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (34c231a0ed74), read on 2026-10-02. The repository is watched and re-audited when it changes.