Linear MCP Server is a Model Context Protocol server implemented in Go that exposes Linear's API operations through the MCP interface. It provides tools for creating, updating, and searching issues; retrieving issues assigned to a user; adding and replying to comments; and fetching team information, all while respecting Linear's rate limits. The server supports URL-aware comment operations, allowing full Linear comment URLs to be passed directly to thread parameters, with automatic resolution to the underlying IDs. It also supports sub-issues (parent-child relationships) and label assignment when creating issues. The server can run in read-only mode by default, with an optional --write-access flag to enable writing operations, and can be configured for various AI assistants via the setup command (e.g., Cline). Prerequisites include a Go 1.23+ toolchain and a Linear API key. The server's version is managed in code and build-time metadata is injected, enabling reproducible releases through GitHub Actions. The server listens for MCP requests on standard input and outputs responses on standard output, making it suitable for integration with LLM tooling and automation pipelines.