Linear MCP Server vs mcp-agent

A side-by-side look at pricing, capabilities, pros, cons, and our editorial scores.

	Linear MCP Server MCP Servers	mcp-agent MCP Servers
Tagline	Open-source MCP server bridging LLM agents to Linear's issue tracker (now deprecated in favour of Linear's official remote MCP)	Python framework for building composable AI agents on the Model Context Protocol
Category	MCP Servers	MCP Servers
Pricing	Free· Free and open source (MIT). Requires a Linear account and personal API key; Linear itself is free for small teams, $8/user/mo Standard, $14/user/mo Plus.	Free· Free and open source (Apache 2.0). LastMile AI offers an optional managed cloud/deployment tier (Beta) with usage-based pricing not publicly listed at time of writing.
Model	—	Provider-agnostic — works with OpenAI (GPT-4o family), Anthropic (Claude 3.5/3.7), Google (Gemini), Azure OpenAI, and AWS Bedrock
Editorial score	—	—
Use cases	Filing bugs from Claude Desktop or Cursor without leaving the editorAgent-driven triage of the inbox projectBulk relabeling or reprioritising issues via natural languageStandup summaries of a user's assigned Linear workAdding comments to tickets from a coding agent's PR reviewReference implementation for building a custom Linear MCP server	MCP-based deep research agentOrchestrator-worker document processingRouter-based customer support triageEvaluator-optimizer content refinement loopsMulti-agent swarm for code reviewDurable long-running research workflows on TemporalExposing an internal agent as an MCP server for Claude DesktopParallel map-reduce over large document setsIntent classification and hand-off between specialist agents
Pros	Open source (MIT) and small enough to read end-to-end in an afternoon One-line install via Smithery or straight npx in Claude Desktop config Covers the create / update / search / comment loop that 90% of ticket workflows need Works with any MCP client, not just Claude Desktop (Cursor, Zed, Continue, custom agents) Clear tool schemas make it a good reference implementation for building your own MCP servers Uses Linear's official GraphQL API, so permissions and audit trails stay intact	MCP-native from the ground up — any MCP server (filesystem, GitHub, Slack, browser, custom) is immediately usable without writing adapters Ships composable implementations of Anthropic's canonical agent patterns (router, orchestrator-worker, evaluator-optimizer, swarm, deep research) Durable execution via Temporal is opt-in — the same agent code runs on asyncio locally and pauses/resumes on Temporal in production Multi-provider: OpenAI, Anthropic, Google, Azure, and AWS Bedrock supported behind a common interface Agents can themselves be exposed as MCP servers, making them callable from Claude Desktop, Cursor, or any MCP-aware client Built-in OpenTelemetry tracing and token accounting for real observability, not just print-debugging Apache 2.0 licensed, active repo (8k+ stars) with regular releases and a healthy examples directory
Cons	Officially deprecated by its author in favour of Linear's own remote MCP server at mcp.linear.app/sse Runs as a local stdio process, so it has to be installed on every workstation and cannot be shared across a team Uses a personal API key, meaning every action shows up as the key owner rather than the actual LLM user Tool coverage is narrower than the official server: no cycles, projects, roadmaps, or workflow state management Error handling and rate-limit backoff are minimal; heavy agent loops can trip Linear's API limits	Python-only — no first-class TypeScript/JavaScript port for teams standardized on Node You still have to run and secure the underlying MCP servers yourself; the framework does not host them for you Durable execution requires operating a Temporal cluster (self-hosted or Temporal Cloud), which is meaningful infra overhead The hosted mcp-agent Cloud deployment product is still labeled Beta, so production-grade managed hosting is not fully mature Fewer prebuilt integrations and less community tutorial content than LangChain/LangGraph, so you will read source more often Rapidly evolving API surface — minor releases still land breaking changes as MCP itself matures
Website	github.com	github.com

Pick Linear MCP Server if

✅ Open source (MIT) and small enough to read end-to-end in an afternoon
✅ One-line install via Smithery or straight npx in Claude Desktop config
✅ Covers the create / update / search / comment loop that 90% of ticket workflows need
✅ Works with any MCP client, not just Claude Desktop (Cursor, Zed, Continue, custom agents)

Pick mcp-agent if

✅ MCP-native from the ground up — any MCP server (filesystem, GitHub, Slack, browser, custom) is immediately usable without writing adapters
✅ Ships composable implementations of Anthropic's canonical agent patterns (router, orchestrator-worker, evaluator-optimizer, swarm, deep research)
✅ Durable execution via Temporal is opt-in — the same agent code runs on asyncio locally and pauses/resumes on Temporal in production
✅ Multi-provider: OpenAI, Anthropic, Google, Azure, and AWS Bedrock supported behind a common interface

Compare a different pair →