Model Context Protocol

Linear MCP Server

Issue Tracking & Project Management via MCP

Allow your AI models to manage software projects. The Linear MCP server provides tools to create issues, update statuses, and search team backlogs.

Development teams use Linear MCP to turn AI conversations into actionable development tasks instantly. Instead of stopping coding to open Linear, create a ticket, fill fields, and assign it, you simply tell your AI agent: 'We need to fix the login bug on Safari' and it creates a properly categorized issue with description, severity, and assignment—all via natural language. This keeps developers in flow state while ensuring no task slips through cracks.

  • ✓Capture bugs and feature requests without leaving chat
  • ✓AI auto-triages and routes issues to correct team/priority
  • ✓Zero context-switching for developers and PMs
  • ✓Keep backlog fresh with AI-generated descriptions
Deploy Managed ServerExplore Integrations
mcp-config.json
{
  "mcpServers": {
    "linear": {
      "command": "sse",
      "args": [
  "https://mcp.linear.app/mcp"
],
      "env": {
        
      }
    }
  }
}
Real-World Automation

Common Workflows

See how teams combine this MCP with other tools to automate real business processes.

Bug Triage Automation

Scenario: A user reports a bug in Slack: 'Login fails on Safari iOS.' AI creates a well-structured Linear ticket, assigns to mobile team, and adds to current sprint.
Steps:
  1. Slack MCP reads the bug report from #support channel
  2. AI extracts: issue type=bug, platform='iOS Safari', component='auth'
  3. Linear MCP creates issue with title '[Bug] Login fails on Safari iOS', priority=High, team='Mobile'
  4. AI adds reproduction steps from user's description and device info
  5. Linear app adds to 'Current Sprint' and assigns to mobile lead
  6. Slack MCP replies in thread: '🚨 Ticket created: Linear.sh/issues/123'
Outcome: Bug-to-triage time drops from ~4 hours (manual) to <30 seconds. Zero lost bugs, accurate categorization.

Feature Request Capture

Scenario: During a customer call, the prospect requests a 'dark mode toggle.' AI instantly captures and logs it to the product backlog.
Steps:
  1. Gmail/Meet transcript (optionally) mentions dark mode request
  2. AI interprets as feature request (not bug), determines impact (high-value customer)
  3. Linear MCP creates issue: 'Feature: Dark mode toggle for dashboard'
  4. Sets cycle to 'Backlog', adds label 'customer-request', priority='High'
  5. Notion MCP updates product requirements doc with request link
  6. Slack MCP posts to #product-requests: 'New feature from Acme (enterprise)'
Outcome: Sales/pre-sales insights flow directly to product team without manual entry. Feature pipeline stays customer-driven.

Automated Standup Task Updates

Scenario: Daily standup: engineer says 'finished auth middleware.' AI updates all related Linear tickets to 'Done.'
Steps:
  1. Engineer voice/text: 'I completed auth middleware refactor and docs.'
  2. AI matches to Linear issues containing 'auth middleware' and 'docs' keywords assigned to speaker
  3. Linear MCP transitions matching issues to 'Done' status
  4. Adds comment: 'Completed in today's standup – fully tested and documented.'
  5. Slack MCP posts confirmation: 'Tickets updated: #456, #457 → Done'
Outcome: Manual ticket status updates eliminated (~15 min/day per engineer). Backlog stays accurate automatically.
Protocol Definition

Available Tools — In Depth

Detailed reference for each tool exposed by this MCP server, with examples and related use cases.

⚒

create_issue

Create a new Linear issue (bug, task, incident, or feature) with title, description, and metadata. Specify team, priority, status, labels, and assignee. Use this to programmatically add items to backlog from AI conversations or external triggers.

Example:""Create bug in 'Mobile' team: 'Login crashes on iOS 17.4 Safari'. Priority=High, labels=['mobile','auth'], assign to @alice.""
Works great with:search_issuesget_my_issues
⚒

search_issues

Search Linear issues by title, description, assignee, status, labels, or team. Returns matching issues with IDs, titles, current status, and assignees. Use this to check if something already exists or to find related work.

Example:""Search for issues assigned to me with status 'In Progress'. Return titles and IDs.""
Works great with:create_issueget_my_issues
⚒

get_my_issues

Shorthand to list all issues assigned to the current user (Linear API token owner). Returns issues grouped by status (Backlog, Todo, In Progress, Done, etc.). Great for quick status checks or daily summary generation.

Example:""What issues are assigned to me and what are their current states?""
Works great with:search_issuescreate_issue
Setup Guide

Configuration & Best Practices

Setup Checklist

  • ✓
    Linear OAuth token (required)
    Go to Linear.app → Settings → API → Create token. Use 'Personal Access Token'. Scope: 'issues:read', 'issues:write', 'team:read'.
  • ✓
    Find your team ID
    Linear URL: linear.app/team/abc123/issues → team ID is 'abc123'. Or use list_workflows equivalent call to discover.
  • ✓
    Webhook setup (optional)
    If using Linear webhooks for real-time sync, configure '/api/linear-webhook' endpoint in Linear Settings → Webhooks.
  • ✓
    User mapping
    Mention '@username' works if username matches Linear display name. Otherwise use Linear user ID.
  • ✓
    Rate limits
    Standard: 120 requests/minute per token. Burst: 150. Exceeding returns 429 with Retry-After.

Troubleshooting

403 Unauthorized / invalid_token
Fix: Token invalid or expired. Regenerate in Linear Settings → API. Ensure scopes include issues:write for creation.
404 team_not_found
Fix: Team ID incorrect or token lacks access to that team. Verify team slug from URL and token permissions.
400 Invalid assignee
Fix: User ID or email doesn't exist in that team. Use correct Linear user ID or email of team member.
429 Rate limited
Fix: Backoff with exponential retry (1s, 2s, 4s). Reduce polling frequency. Consider batch operations.
Rate limit: 120 requests/minute per token. Burst up to 150. Rate limit headers provided.

When to Use Linear MCP Server vs. Alternatives

Use This MCP When:

  • You need AI-native access via natural language
  • Your workflows span multiple tools (MCP composability)
  • You prefer cloud hosting over local Docker
  • You want zero-config deployment with ClawFast
  • Your use case requires LLMs to reason and act autonomously

Consider Alternatives When:

  • You need bulk data sync (use native export/import)
  • Real-time streaming is critical (use native webhooks)
  • You have strict compliance requiring direct API audit logs
  • Your integration is a one-off script (direct SDK may be simpler)
  • You need features not yet exposed by this MCP server
FAQ

Common Questions About Linear MCP Server

Q: Can I update existing issues?
A: Yes, using Linear's update API (not directly via this basic MCP). However you can add comments or change status via related tools. Full update requires extended MCP methods or n8n workaround.
Q: What issue types are supported?
A: Bug, Task, Incident, Feature, Story, Epic (depends on your Linear workspace schema). All standard Linear types supported.
Q: Can I attach files or images?
A: Not via basic MCP. Attachments require Linear's upload API—consider n8n workflow to handle file uploads then attach to issue.
Q: Projects & cycles support?
A: Cycle (sprint) assignment supported by setting cycle property. Projects supported via 'project' field if present in workspace schema.
Q: Custom fields?
A: Yes—Linear custom fields (text, select, date) can be set if present in your workspace. Need to know field ID; consider using direct API for complex fields.
Q: Does it support sub-issues/child tasks?
A: Basic MCP doesn't include hierarchical operations. You can create sub-issues and set parent ID via additional parameters if supported by server.
Q: Team vs. workspace scope?
A: API token is workspace-scoped. You can access all teams you're a member of. Specify teamId in create_issue to target correctly.
Q: Webhooks from Linear?
A: Linear has excellent webhooks for issue created/updated/deleted. You can use a separate webhook-receiver MCP to trigger AI responses on ticket changes.
Customer Success

Success Story: NovaTech (fast-growing startup)

Challenge

Product team struggled with backlog bloat—500+ stale issues, ambiguous priorities. Engineers spent 2 hrs/week manually updating ticket statuses after standup.

Solution

Deployed Linear MCP + Slack MCP. Created 'daily digest' workflow: AI reads all 'In Progress' issues, composes summary to Slack, and prompts engineers to mark Done items. Also built voice-triggered ticket creation for mobile devs.

Results

  • ✓ Stale tickets reduced 80% (500 → 100 actively maintained)
  • ✓ Engineer admin time: 2 hrs/week → 5 minutes
  • ✓ Standup automated—Slack digest posted daily at 9:15 AM
  • ✓ Feature request capture from customer calls instant, no forgetting
"Our Linear finally feels alive. Issues get created right when we talk about them. Status stays accurate automatically. It's like having a project manager who never misses a detail."
— Elena Torres, Engineering Manager, NovaTech

Combine with Other MCPs

This MCP works great alongside other tools. Here are popular combinations.

slack
Post ticket updates and new issues to relevant Slack channels
→
notion
Sync Linear epics to Notion product roadmap for stakeholder visibility
→
github
Link Linear issues to GitHub PRs (via webhook or n8n)
→
firecrawl
Create bugs automatically from scraped error logs or user feedback
→

Ready for full workflows?

Check out our integration page for Linear MCP Server to see complete AI agent templates and step-by-step guides.

View Linear MCP Server Integrations →

Technical Specifications

Protocol
SSE (Server-Sent Events) via Linear's hosted MCP endpoint
Transport
HTTPS (TLS 1.3)
Authentication
Bearer token (Linear Personal Access Token)
Rate Limit
120 requests/minute per token
Typical Latency
300-700ms
Data Format
JSON (Linear issue schema)
Supported LLMs
Claude 3.5+, GPT-4o, Kimi K2.5
Hosting
Linear's hosted MCP bridge (mcp.linear.app)
Uptime SLA
Linear's availability (99.9%+)
Last Updated
Real-time via Linear API

Why Managed MCP?

Model Context Protocol (MCP) is the new standard for AI connectivity. While you can host servers locally, ClawFast provides a production-grade managed environment.

  • 24/7 Availability: No need to keep your local machine running.
  • Secure Secrets: API keys are encrypted at rest and never exposed to logs.
  • SSE Protocol: Native Server-Sent Events (SSE) support for cloud-to-cloud connectivity.
  • Zero Config: One-click deployment with pre-configured templates.

Looking for more ways to use Linear MCP Server?

Explore our high-level integration page for Linear MCP Server to see business use cases and ready-to-use AI agent templates.

View Linear MCP Server Integrations →

Connect Linear MCP Server to your AI stack today

Deploy your managed MCP server in under 60 seconds.

Start Free Deployment