linear-mcp-lean
Related Servers
Alternatives to linear-mcp-lean
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityDmaintenanceSelf-hosted MCP server with 83+ tools for AI workflows. Features 80%+ token reduction through 5 optimization layers.-
- AlicenseNot gradedqualityCmaintenanceMCP server that cuts cloud LLM costs 36-42% by indexing context locally and giving agents precision retrieval tools instead of raw context dumps.9 npm7MIT
- AlicenseNot gradedqualityCmaintenanceA local-first MCP server that reduces LLM token usage by intercepting, deduplicating, compressing, and optimizing MCP tool calls and responses.1 npmMIT
- AlicenseAqualityCmaintenanceMCP server that reduces token consumption in AI coding assistants by up to 90% via structural reads, PreToolUse hooks, and tp-\* subagents.25189 npm5MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that reduces AI agent token usage by up to 90% through intelligent context compression. Enables efficient code exploration, multi-file refactoring, and debugging by providing tools for smart reading, searching, and managing code context.4MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that reduces token usage for AI coding agents by providing structural code outlines and minification for .NET projects.4MIT
TDQS
Scored across 36 tools
Each tool targets a distinct operation on a specific entity (issue, project, document, etc.). Even similar pairs like create_attachment vs create_attachment_from_upload are clearly differentiated by their parameters and process. The raw GraphQL tool is explicitly a fallback, avoiding ambiguity.
Tool names consistently follow a verb_noun pattern (e.g., create_issue_label, list_issues, save_issue). The only deviation is linear_graphql, but that is a special-purpose tool, and the pattern holds for all others. Naming is predictable and uniform.
With 36 tools, the server is comprehensive but slightly heavy. It covers many Linear entities, but the count is above the typical well-scoped range (3–15). Some tools like extract_images and search_documentation are auxiliary, and the diff-related tools add redundancy. Still, the count is reasonable given the domain's complexity.
The tool surface lacks delete operations for issues, projects, documents, attachments, comments, milestones, and labels. There are no update operations for labels or comments (save_comment only creates, not updates). These gaps force agents to rely on the raw graphql tool for basic lifecycle management, which is a significant shortcoming.