/ Verzeichnis / Playground / Linear
● Offiziell linear 🔑 Eigener Schlüssel nötig

Linear

von linear · linear/linear

Lassen Sie Ihren Agenten Ihren Linear-Backlog durchsuchen, Zyklusaktualisierungen veröffentlichen und Fehler aus Sentry melden – ohne die App öffnen zu müssen.

Das offizielle Remote-MCP (SSE) von Linear legt Probleme, Projekte, Zyklen, Teams, Kommentare und Benutzer offen. OAuth wird von Linear verwaltet, daher muss kein PAT verwaltet werden. Am besten kombinierbar mit Sentry (Auto-File-Bugs), GitHub (Link-PRs) und Notion (wöchentliche Berichte).

Warum nutzen

Hauptfunktionen

Live-Demo

In der Praxis

linear.replay ▶ bereit
0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "linear": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.linear.app/sse"
      ]
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "linear": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.linear.app/sse"
      ]
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "linear": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.linear.app/sse"
      ]
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "linear": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.linear.app/sse"
      ]
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "linear",
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.linear.app/sse"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json
{
  "context_servers": {
    "linear": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mcp-remote",
          "https://mcp.linear.app/sse"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add linear -- npx -y mcp-remote https://mcp.linear.app/sse

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: Linear

So sortieren Sie einen chaotischen linearen Rückstand in 10 Minuten

👤 Technische Manager, technische Leiter ⏱ ~15 min intermediate

Wann einsetzen: Montagmorgen. Der Rückstand umfasst mehr als 200 nicht geprüfte Probleme und die Planung erfolgt in einer Stunde.

Voraussetzungen
  • Linearer Zugriff auf den Arbeitsbereich — OAuth über „mcp-remote“ – der erste Tool-Aufruf öffnet den Browser zur Gewährung
  • Team-Slug (z. B. „ENG“) — Schauen Sie sich jede Problemkennung an – das Präfix ist Ihr Team-Slug
Ablauf
  1. Rufen Sie alle nicht geprüften Probleme für das Team ab
    Listen Sie alle ENG-Probleme im Status „Triage“ oder ohne festgelegte Priorität auf, die in den letzten 30 Tagen erstellt wurden. Rückgabe-ID, Titel, Reporter und Beschreibungslänge.✓ Kopiert
    → Kandidatentabelle mit genügend Kontext zur Klassifizierung
  2. Nach Themen gruppieren
    Gruppieren Sie diese in 4–6 Themen (Bug/Infra/Onboarding/Perf/usw.). Schlagen Sie für jeden Cluster eine Priorität und ein vorgeschlagenes Projekt vor.✓ Kopiert
    → Themed clusters with rationale
  3. Apply the decisions
    For each cluster, update the issues: set priority, add the matching label, and move to 'Backlog' state. Do NOT assign anyone.✓ Kopiert
    → N issues updated, confirmations logged

Ergebnis: Ein planungsbereiter Rückstand, gruppiert und priorisiert, mit einem Prüfprotokoll für jede vom Agenten vorgenommene Änderung.

Fallstricke
  • Agent mass-assigns issues to the wrong people based on 'who wrote similar code' — Explicitly tell it NOT to assign — assignment is a human call and should stay that way
  • Free-tier Linear rate-limits you after ~1500 requests/h — Batch updates with issueBatchUpdate when available; otherwise keep triage runs under 500 issues
Kombinieren mit: sentry · github

Generate a weekly cycle status report from Linear

👤 Engineering managers, PMs ⏱ ~10 min beginner

Wann einsetzen: Friday afternoon, you need to write the weekly update for leadership.

Voraussetzungen
  • Active cycle in Linear — Linear > your team > Cycles — note the current cycle number
Ablauf
  1. Pull cycle stats
    For ENG cycle 47, list all issues grouped by state. Include completed-this-week, in-progress, blocked, and at-risk (no update in 3+ days).✓ Kopiert
    → Breakdown with counts and issue titles
  2. Diff against last week
    Compare to last week's snapshot [paste prior JSON]. What shipped, what regressed to earlier states, what's newly blocked?✓ Kopiert
    → Delta with narrative
  3. Draft the report
    Write a 1-page Markdown report: wins, in-flight, blockers, help-needed. Keep it honest — leadership reads between the lines.✓ Kopiert
    → Report ready to paste into Slack or Notion

Ergebnis: A polished cycle update in 10 minutes instead of 45.

Fallstricke
  • Completed issues without merged PRs look like progress but aren't — Combine with GitHub MCP — verify each 'Done' issue has a merged PR referenced
Kombinieren mit: github · notion

Auto-file Linear bugs from new Sentry issues

👤 On-call engineers ⏱ ~15 min intermediate

Wann einsetzen: You want real-time error spikes in Sentry to become tracked bugs without manual copy-paste.

Voraussetzungen
  • Sentry MCP installed alongside Linear — See the sentry guide for setup
  • A dedicated Linear label like from-sentry — Linear > Settings > Labels — create once
Ablauf
  1. Find new Sentry issues over threshold
    Find Sentry issues first seen in the last 24h with >50 events in the web-prod project.✓ Kopiert
    → List with issue IDs and event counts
  2. Check for duplicates in Linear
    For each Sentry issue title, search Linear for existing issues with similar titles or containing the Sentry URL. Skip ones already filed.✓ Kopiert
    → Dedupe list — only genuinely new items
  3. Create the Linear bugs
    Create a Linear issue in ENG team for each new Sentry issue: title = Sentry title, description = stacktrace + link, priority = Urgent if >1000 events else High, label = from-sentry.✓ Kopiert
    → N issues created with links returned

Ergebnis: A clean Linear bug intake that never drops a production error on the floor.

Fallstricke
  • Same Sentry issue gets filed twice because titles drift slightly — Use the Sentry issue short-id (e.g. WEB-3a91) in the Linear title and dedupe on that substring
Kombinieren mit: sentry

Nudge stale issues in the current cycle

👤 Tech leads, scrum masters ⏱ ~5 min beginner

Wann einsetzen: Mid-cycle check. Issues assigned for 5+ days with no state change are usually stuck.

Ablauf
  1. Find the stale issues
    List issues in the current ENG cycle that have been in 'In Progress' for 5+ days without a state change or comment.✓ Kopiert
    → List with assignee and days-stale
  2. Post a gentle nudge comment
    Add a comment on each: 'Quick check-in — still on track for this cycle, or do you need to break this down / get help?' Tag the assignee.✓ Kopiert
    → Comments posted, links returned
  3. Escalate if ignored
    In 48 hours, re-run. If still no update, DM me a list for 1:1 follow-up.✓ Kopiert
    → Escalation list for human follow-up

Ergebnis: Unblocked work without being the nagging manager every day.

Fallstricke
  • Comment spam if you run this hourly — Check if the agent has already commented in the last 3 days before posting again

Scaffold a Linear project from a Notion spec

👤 PMs, tech leads starting a new initiative ⏱ ~20 min intermediate

Wann einsetzen: You have a written PRD and need to break it into trackable issues.

Voraussetzungen
  • Notion MCP installed — See notion guide
  • The PRD page URL — Copy from Notion
Ablauf
  1. Read and summarize the spec
    Read the Notion PRD at <URL> and list every discrete deliverable as a one-line description.✓ Kopiert
    → 15-40 candidate issues
  2. Review and refine
    Group these into 3-5 milestones. Flag any that need design, API, or DB work as separate issues.✓ Kopiert
    → Structured issue tree
  3. Create the Linear project and issues
    Create a Linear project named '<Spec title>' in ENG team. Create each milestone as a parent issue, with children as sub-issues. Link back to the Notion page in each description.✓ Kopiert
    → Project URL + issue count

Ergebnis: A fully-scaffolded Linear project in 20 minutes instead of 2 hours of manual ticket writing.

Fallstricke
  • Agent creates 80 issues when you wanted 20 — too granular — In step 2, explicitly cap: 'no more than 20 issues total, merge anything smaller than a day of work'
Kombinieren mit: notion

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

linear + sentry

Turn production error spikes into tracked Linear bugs automatically

Find new Sentry web-prod issues from the last 24h with >50 events. For each, create a Linear bug in ENG team labeled 'from-sentry', priority High, with the stacktrace in the description.✓ Kopiert
linear + github

Auto-link PRs to Linear issues and close issues when PRs merge

For every open PR in my repo, find the Linear issue ID in the title or branch name and add a reference comment on the Linear issue with the PR URL.✓ Kopiert
linear + notion

Post weekly cycle digests to a Notion database

Generate this week's ENG cycle status and create a page in the Notion 'Engineering Weekly' database with the full report.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

WerkzeugEingabenWann aufrufenKosten
list_issues team?, assignee?, state?, label?, cycle?, query?, limit? Primary search — filter the stream 1 API call
get_issue id Fetch full context for a single issue 1 API call
create_issue teamId, title, description?, priority?, labelIds?, assigneeId?, projectId? File a new issue 1 API call
update_issue id, stateId?, priority?, assigneeId?, labelIds?, title?, description? Change state, priority, or assignment 1 API call
create_comment issueId, body Post a nudge or status note on an issue 1 API call
list_projects teamId? Discover active projects in a team 1 API call
list_cycles teamId Find active or recent cycles for a team 1 API call
list_teams Discover teams in the workspace 1 API call

Kosten & Limits

Was der Betrieb kostet

API-Kontingent
1500 req/h for OAuth apps, 120 req/min burst — generous for any real workflow
Tokens pro Aufruf
300–1500 tokens per issue depending on description/comments
Kosten in €
Free — Linear MCP is included in any Linear plan
Tipp
Use list_issues with specific filters instead of pulling everything then filtering — cuts token cost 10x on large backlogs

Sicherheit

Rechte, Secrets, Reichweite

Minimale Scopes: read write issues:create
Credential-Speicherung: OAuth via mcp-remote — tokens stored in ~/.mcp-auth/, refreshable without re-logging-in
Datenabfluss: All calls to api.linear.app and mcp.linear.app
Niemals gewähren: admin

Fehlerbehebung

Häufige Fehler und Lösungen

OAuth browser popup doesn't open

Run npx -y mcp-remote https://mcp.linear.app/sse manually once — it'll print a URL you can paste into a browser

Prüfen: After auth, re-run your agent; token cached in ~/.mcp-auth/
403 on update_issue

Your Linear role lacks write access to that team. Ask a workspace admin to promote you or scope the agent to a team you own.

Issues returned but comments are missing

Comments are a separate query — use get_issue with include-comments, or list comments separately with the issue ID.

Can't find an issue you know exists

Check the team filter — issues in other teams aren't returned unless you pass team=null or specify that team.

Alternativen

Linear vs. andere

AlternativeWann stattdessenKompromiss
Jira MCPYour org is on Jira, not LinearHeavier API, more states/fields to reason about — agents do worse on Jira out of the box
GitHub Issues (via GitHub MCP)You want issues tightly coupled to code without a separate toolLose cycles, projects, and workflow states — GitHub Issues is simpler but less structured

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen