MCP Server

Project ManagementIssue TrackingSprint PlanningMIT

Linear MCP Server

Q: What is the Linear MCP Server?

Linear MCP Server is a Model Context Protocol integration that connects AI coding assistants directly to Linear's project management platform. It exposes issue creation, status updates, sprint planning, label management, comment threads, and backlog queries as MCP tools. Your agent can triage bugs, plan sprints, update issue statuses, and generate progress reports without ever leaving the IDE.

Q: How do I authenticate the Linear MCP Server?

The server uses a Linear API key or personal access token for authentication. Generate a token in Linear under Settings, then API, then Personal API Keys. Pass it to the MCP server through the LINEAR_API_KEY environment variable. The token inherits the permissions of your Linear account, so the agent can access all teams and projects you have access to.

Q: Can the agent create and assign issues automatically?

Yes. The agent can create new issues with full metadata — title, description in Markdown, priority level, labels, project assignment, cycle placement, and team member assignment. It can also batch-create multiple issues from a feature breakdown, link related issues as blocked/blocking relationships, and add sub-issues for complex tasks that need decomposition.

Q: Does Linear MCP support sprint planning workflows?

Absolutely. The agent can query the backlog for unassigned or unprioritized issues, estimate complexity based on issue descriptions, assign issues to upcoming cycles (Linear's term for sprints), balance workload across team members by checking current assignments, and generate sprint summaries. It transforms sprint planning from a meeting-heavy process into an agent-assisted workflow.

Q: Can I query issues with complex filters?

Yes. The MCP server supports Linear's powerful filtering system. You can query issues by status, assignee, label, priority, project, cycle, created date, updated date, and custom fields. The agent can combine filters to answer questions like "show me all high-priority bugs assigned to the frontend team that are blocked" or "list issues that have been in review for more than three days."

Q: How does Linear MCP integrate with code workflows?

Linear MCP bridges project management and coding seamlessly. When the agent fixes a bug, it can update the corresponding Linear issue status from "In Progress" to "Done" and add a comment with the commit reference. When creating a pull request via GitHub MCP, the agent can link it to the Linear issue. This keeps project tracking in sync with actual code changes without manual status updates.

by Linear / Community · anthropic/mcp-linear

Linear MCP Server connects your AI coding assistant directly to Linear's project management platform. Create issues, update statuses, plan sprints, query backlogs, manage labels, and generate progress reports — all through natural language commands from Claude Code or any MCP-compatible client. Stop context-switching between your IDE and the project tracker.

Developers spend a surprising amount of time on project management overhead — updating issue statuses, writing sprint summaries, triaging incoming bugs, and keeping stakeholders informed. Linear MCP automates this busywork by letting your agent handle issue lifecycle management while you focus on writing code. When you finish a task, the agent updates Linear. When a bug report arrives, the agent creates and categorizes the issue. When sprint planning time comes, the agent prepares the backlog analysis.

20+

Tools Exposed

create, query, update, plan...

<2min

Setup

npm install + API key

Linear

Platform

issue tracking & PM

MIT

License

open source

Quick Install

claude mcp add linear -- npx @anthropic/mcp-linear

Key Features

Issue Lifecycle Management

Create, read, update, and close issues with full metadata support. Set titles, descriptions in Markdown, priority levels (Urgent through No Priority), labels, assignees, project assignments, and due dates. Transition issues through custom workflow states seamlessly.

Sprint & Cycle Planning

Query backlog items, estimate story points, assign issues to cycles, and balance workload across team members. The agent can analyze current velocity, suggest scope adjustments, and generate sprint commitment summaries that account for team capacity and historical throughput.

Advanced Issue Queries

Filter issues across any combination of status, assignee, label, priority, project, cycle, and date range. Ask natural language questions like "what urgent bugs are unassigned" or "which issues have been in review for over a week" and get instant structured results.

Comment & Discussion Threads

Add comments to issues with rich Markdown formatting, mention team members, attach code snippets, and respond to existing discussion threads. Keep all context about a task — decisions, blockers, implementation notes — centralized in the issue timeline.

Label & Project Organization

Create and manage labels for categorizing issues by type (bug, feature, chore), area (frontend, backend, infra), or any custom taxonomy. Organize issues into projects for feature-level tracking and use sub-issues for task decomposition of complex work items.

Progress Reporting

Generate sprint velocity reports, burndown summaries, and backlog health assessments. The agent can calculate completion rates, identify blocked items, highlight overdue issues, and produce formatted status updates suitable for stakeholder communication or team standups.

Execution Brief

Use this page as a rollout checklist, not just reference text.

Suggest update

Tool Mapping Lens

Organize Tools by Workflow Phase

Catalog-oriented pages work best when users can map discovery, evaluation, and rollout in a clear path instead of reading an undifferentiated list.

Define the job-to-be-done first
Group tools by stage
Prioritize by adoption friction

Actionable Utility Module

Skill Implementation Board

Use this board for Linear MCP Server before rollout. Capture inputs, apply one decision rule, execute the checklist, and log outcome.

Input: Objective

Deliver one measurable improvement with linear mcp server claude code issue tracking project management sprint planning agile workflow

Input: Baseline Window

20-30 minutes

Input: Fallback Window

8-12 minutes

Decision Trigger	Action	Expected Output
Input: one workflow objective and release owner are defined	Run preview execution with fixed acceptance criteria.	Go or hold decision backed by repeatable evidence.
Input: output quality below baseline or retries increase	Limit scope, isolate root issue, and rerun controlled test.	One confirmed correction path before wider rollout.
Input: checks pass for two consecutive replay windows	Promote to broader traffic with fallback path active.	Stable rollout with low operational surprise.

Execution Steps

Record objective, owner, and stop condition.
Execute one controlled preview run.
Measure quality, latency, and correction burden.
Promote only when pass criteria are stable.

Output Template

tool=linear mcp server claude code issue tracking project management sprint planning agile workflow
objective=
preview_result=pass|fail
primary_metric=
next_step=rollout|patch|hold

Share execution feedback

What Is Linear MCP Server?

Linear MCP Server is a Model Context Protocol bridge that connects AI coding assistants to Linear's project management platform. It exposes issue tracking, sprint planning, backlog management, and reporting operations as MCP tools that Claude Code, Cursor, or any compatible client can call directly from the IDE. This eliminates the constant context-switching between code editor and project tracker that fragments developer focus.

Project management is a necessary overhead that every development team faces, but the mechanics of creating issues, updating statuses, writing comments, and planning sprints are repetitive tasks perfectly suited for AI automation. Linear MCP lets the agent handle this administrative layer while developers stay in their coding flow. Finish implementing a feature, tell the agent, and it updates the issue, adds implementation notes, and moves it to review — all without opening a browser tab.

The server leverages Linear's GraphQL API with optimized query patterns that minimize API calls while maximizing the data available to the agent. Issue queries return related context — comments, linked issues, project membership, and cycle assignment — in a single request. This allows the agent to make informed decisions about issue triage, priority adjustment, and sprint scope without multiple round trips.

Linear MCP integrates powerfully with other MCP servers in the ecosystem. GitHub MCP links pull requests to Linear issues for end-to-end traceability. Slack MCP posts sprint summaries and status updates to team channels. Filesystem MCP reads local changelogs and release notes to automatically update related issues. Together they create a fully connected development workflow where project tracking, code management, and team communication stay in sync automatically.

How to Calculate Better Results with linear mcp server claude code issue tracking project management sprint planning agile workflow

Install the Linear MCP server package via npm. The package is lightweight with minimal dependencies and communicates with Linear through its public GraphQL API. No additional Linear integrations or webhook configurations are required for basic operation.

Generate a Linear API key by navigating to Linear Settings, then clicking API in the sidebar, then creating a new Personal API Key. This key grants access to all teams and projects your account can see. Pass it to the MCP server through the LINEAR_API_KEY environment variable. For team-wide use, consider creating a dedicated service account with appropriate access scope.

Register the MCP server with your AI client using the quick install command. For Claude Code, this adds Linear tools to your available toolkit immediately. Optionally set LINEAR_TEAM_KEY to a default team identifier so the agent targets the correct team without asking each time.

Verify the setup by asking your agent to list recent issues from your team or query the current sprint. If issues appear with correct titles, statuses, and assignees, the connection is working. Try creating a test issue with a label and priority to confirm write access, then delete it to confirm full CRUD capabilities.

Treat this page as a decision map. Build a shortlist fast, then run a focused second pass for security, ownership, and operational fit.

When a team keeps one shared selection rubric, tool adoption speeds up because evaluators stop debating criteria every time a new option appears.

Worked Examples

Automated bug triage from error monitoring

Your application's error monitoring service reports a spike in unhandled exceptions on the checkout page, and you need to create actionable Linear issues from the error data
Ask the agent to read the error logs from the monitoring dashboard (via browser automation or API), group errors by stack trace signature, and identify the three most frequent error types
The agent creates a Linear issue for each unique error, setting the title to a human-readable error summary, the description to the full stack trace with occurrence count, priority to Urgent for errors affecting checkout, and labels to "bug" and "checkout"
Each issue is assigned to the team member who last modified the affected file (identified via GitHub MCP's blame data) and placed in the current sprint cycle
The agent links related issues as "blocked by / blocking" relationships when errors share a common root cause, creating a clear dependency graph for the fix sequence
A summary comment is posted to the team's Slack channel via Slack MCP with the issue links, affected user count, and suggested investigation order based on impact severity

Outcome: Structured, prioritized, and assigned bug tickets created from raw error data in under a minute — with cross-references, dependency links, and team notifications — replacing a manual triage process that typically takes an entire standup meeting.

Sprint planning with velocity-based scope recommendations

The team is starting a new two-week sprint and needs to pull items from the backlog into the upcoming cycle based on team capacity and historical velocity
Ask the agent to analyze the last three completed sprints using Linear MCP, calculating average points completed per sprint, completion rate, and carryover percentage for each team member
The agent queries the backlog for prioritized items, filters by the team's focus areas (labels matching current OKR themes), and sorts by priority and age
Based on historical velocity data, the agent recommends a sprint scope — specific issues totaling the team's average capacity minus a 15 percent buffer for unplanned work — and assigns each issue to the team member with the most relevant expertise and available capacity
The agent creates the new cycle in Linear, moves the recommended issues into it, and generates a sprint commitment summary with the total points, breakdown by team member, key deliverables, and identified risks
The summary is posted as a comment on the cycle and shared to the team Slack channel, ready for the team to review and adjust before committing

Outcome: A data-driven sprint plan assembled in minutes that accounts for individual velocity, team capacity, and strategic priorities — turning sprint planning from a one-hour meeting into a five-minute review-and-approve workflow.

Frequently Asked Questions

What is the Linear MCP Server?