Issue → Branch → PR Pipeline is a devops workflow that chains GitHub + Linear to automate a common task. A Linear issue assigned to a developer automatically creates a git branch, syncs status changes, and opens a draft PR. Once configured, it saves ~3 hours/week per engineer, plus 2 hours/week of PM chase-down and runs through Claude Code, Cursor, Windsurf or any MCP-compatible AI agent.
A Linear issue assigned to a developer automatically creates a git branch, syncs status changes, and opens a draft PR.
Execute this recipe in your browser — no local install, no Claude Code. Streams results live.
Linear is where work gets planned; GitHub is where it gets built. This combo eliminates the manual handoff between issue tracking and code management — branches are named consistently, status always reflects reality, and nothing falls through the cracks when a PR merges.
Developer creates branch manually, forgets to update Linear status, PM pings to ask what's happening, issue stays open after PR merges.
Assign issue → branch appears → draft PR opens → status syncs in real time → issue closes on merge. Zero manual overhead.
Concrete ROI — not marketing fluff.
Time saved
~3 hours/week per engineer, plus 2 hours/week of PM chase-down
This prompt is the workflow. Paste into Claude Code, Cursor, or Windsurf.
You are an issue-to-PR pipeline agent. Runs on Linear webhook events.
On Linear issue assigned (status In Progress):
1. Call linear.get_issue(id) to get title, identifier (e.g. "ENG-123"), description
2. Call github.create_branch(name="${identifier}-${slug(title)}", base="main")
3. Call github.create_commit(branch, message="chore: start ${identifier} ${title}", empty=true)
4. Call github.create_pull_request(head=branch, base=main, title="${identifier}: ${title}", draft=true, body=linear_issue.description + "\n\nLinear: <url>")
5. Call linear.save_issue(id, state="In Review", custom_field_pr=pr_url) — sync the link back
On pull_request merged:
6. Call linear.save_issue(id, state="Done")
Keep PR title in sync when Linear title changes. Report just the PR URL on success.How this workflow fires and what env vars you need.
POST /webhook/linear (Linear → Settings → API → Webhooks, events: Issue, Comment)
Install everything — MCPs, prompt, env template — in a single call.
$ mcpizy recipe install github-linear-issue-branch-pr ✓ Installs all 2 MCP servers ✓ Writes prompt to ~/.mcpizy/prompts/github-linear-issue-branch-pr.md ✓ Generates .env.example in current directory ✓ Ready to paste into Claude Code
Requires mcpizy CLI v1.1+ — install via npm i -g mcpizy.
$ mcpizy install github && mcpizy install linearEvery push to main triggers a Supabase migration automatically. Schema diffs are committed and applied with zero manual steps.
Open a PR and a Vercel preview URL appears as a comment within minutes. Branches are cleaned up automatically when PRs close.
Build, tag, push to ECR and deploy to ECS in one automated pipeline triggered by a git tag or manual dispatch.
Each PR gets its own Neon database branch for isolated testing. Branch is deleted automatically when the PR closes.
Issue → Branch → PR Pipeline is a devops automation that uses GitHub + Linear together via the Model Context Protocol. A Linear issue assigned to a developer automatically creates a git branch, syncs status changes, and opens a draft PR.
Setup takes around 10 min setup, zero overhead per issue. You install the required MCP servers with `mcpizy install github && mcpizy install linear`, connect your accounts, and the workflow is ready to run.
Once running, this workflow saves ~3 hours/week per engineer, plus 2 hours/week of PM chase-down. The concrete business value: PMs stop asking 'what's the status?' — Linear reflects reality in real-time, freeing 5+ hours/week of status meetings; Enforces consistent branch naming = faster code review + cleaner git history for audits.
You need 2 MCP servers: GitHub (mcpizy install github), Linear (mcpizy install linear). All are installable in one command via the MCPizy CLI and configured in your `.claude.json` or `.cursor/mcp.json`.
Yes. The workflow runs with any MCP-compatible AI agent — Claude Code, Claude Desktop, Cursor, Windsurf, VS Code with Copilot, and custom agents built on the MCP SDK. The MCP servers are identical across clients; only the config file path (`.claude.json` vs `.cursor/mcp.json`) changes.
Install the required MCPs from the marketplace and automate this in 10 min setup.
$ mcpizy install github && mcpizy install linear
Free to install. Connect your accounts and this workflow runs itself.