MCP Workflow for Automated Release Notes.
PRs merged, builds validated, changelogs written, release pages published , generate polished release notes without copy-pasting commits
Works with every AI agent you already use
…and any MCP-compatible client
Waiting for input…
Gemini How It Works
Your AI agent reads all merged PRs from GitHub since the last tagged release , 23 PRs merged in the last 2 weeks.
It parses each PR title using conventional commit format: 'feat(auth): add MFA support' becomes a Feature. 'fix(payments): handle null amount' becomes a Bug Fix.
'BREAKING: remove v1 API endpoints' gets flagged as a Breaking Change. For each PR, the agent checks Buildkite , did the CI pipeline pass? PR #142 failed on the security scan step.
The agent flags it: 'Warning: PR #142 merged with failing security scan.' Then it groups everything: 4 features, 12 bug fixes, 2 performance improvements, 1 breaking change, 4 chores.
It creates a Notion page titled 'Release v2.15.0 , June 3, 2026' with categorized sections, PR links, author attribution, and a migration guide for the breaking change.
The page is added to your Releases database with status 'Draft' for final review.
MCP Server Orchestration: 3 MCP Servers, one intelligent agent
Connect GitHub, Buildkite and Notion MCP servers so your AI agent reads all merged pull requests since the last release, verifies each one passed CI in Buildkite, groups changes by category (features, fixes, breaking changes), and publishes a formatted release page in your Notion workspace. Engineering teams shipping weekly releases spend hours compiling changelogs from git logs. The agent does it in seconds. No missed PRs. No forgotten breaking changes. One prompt and your release notes are published.
Github
triggerReads merged PRs, commit messages and branch history
list_pull_requests get_file_contents get_repository_details search_github_code Buildkite
actionValidates CI status for each PR and build artifacts
list_pipeline_builds get_build get_pipeline list_pipelines Notion
actionCreates formatted release pages in the engineering wiki
create_page query_database search_pages get_database Run This Automation Today
Connect Claude, ChatGPT, Cursor, or any AI agent to the Vinkius catalog and run this automation in minutes.
Build Your Own MCP
Turn any internal API into an MCP server. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Connect & Automate
The 3 servers this recipe uses are ready in the catalog. Connect them once, paste a prompt, and your AI runs the full workflow.
- Github, Buildkite & Notion ready in the catalog right now
- Add more from 4,700+ servers whenever you need
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers and recipes added every week
Superpowers you didn't know your AI had
The Vinkius catalog gives your agent access to 4,700+ MCP servers and the intelligence to combine them. Imagine never logging into another dashboard. Your AI handles the work across every tool, in one conversation. That's what this infrastructure was built for.
Cross-Platform Intelligence
Your agent doesn't just connect to tools. It understands the relationships between them. Data flows where it needs to go, automatically, with full context preserved across every platform.
Contextual Reasoning
Every decision your agent makes considers the full picture. It reads CRM data, checks calendars, reviews conversation history, and acts on everything at once. Not step by step. All at once.
Productivity at Scale
What used to take 45 minutes across five different dashboards now takes one sentence. Your agent runs the entire workflow end to end while you focus on decisions that actually matter.
Zero-Config Reliability
No API keys to paste. No webhooks to configure. No YAML to debug. Connect your MCP servers once, and your agent handles the rest. Every time, without intervention.
Made for
exactly this
Your AI agent taps into the entire Vinkius MCP catalog to handle these for you. You describe what you need. It does the rest.
Engineering teams shipping weekly or biweekly releases who spend 1-2 hours manually compiling changelogs from merged PRs
Developer advocates who need polished, categorized release notes for external communication without reading every commit
Product managers who need to know what shipped in each release without asking engineers to summarize their PRs
Open-source maintainers who want automated CHANGELOG generation with contributor attribution
Frequently Asked Questions About This MCP Server Orchestration
Which MCP servers do I need for this workflow?
Three: GitHub, Buildkite and Notion. Connect all three to your AI client before running any prompt from this page.
Does this work with Claude Desktop, Cursor or Windsurf?
Yes. Any AI client that supports the Model Context Protocol works , Claude Desktop, Cursor, Windsurf, Cline and others.
What if my team does not use conventional commits?
The agent falls back to analyzing PR titles and descriptions for keywords. 'Added,' 'Fixed,' 'Improved,' 'Removed' , these are enough to categorize most changes.
Can I customize the Notion page template?
Yes. Describe the structure in your prompt: 'Use these sections: What is New, Bug Fixes, Known Issues. Include screenshots from PR descriptions.' The agent will adapt.
Does it handle monorepos?
Yes. The agent reads the file paths in each PR to determine which package or service was affected and can group changes by service.
Can I use this with GitLab instead of GitHub?
Yes. Replace the GitHub MCP server with the GitLab MCP server. The workflow logic remains the same , the agent reads merge requests instead of pull requests.
Deploy Containers to Production Using MCP
Code pushed, images built, tags verified, deploys triggered, status reported , ship containers from commit to production in one prompt
Extract Architecture Principles Using MCP
Code patterns formalized, universal laws derived, causal forces identified , replace ad-hoc architecture with mathematical proof
Find Codebase Duplications Using MCP Servers
Your codebase has 4 different implementations of date formatting, 3 versions of the retry logic, and 2 competing validation libraries , but nobody knows because grep only finds exact matches and these duplicates are semantic
Generate Error Postmortems Automatically via MCP
Errors captured, stack traces analyzed, root cause commits identified, postmortem docs generated , write incident reports without the pain
How MCP Servers Auto-Triage Bug Reports
New bugs detected, severity classified, sprint tickets created, team notified , triage your backlog without a standup
MCP Recipe for Code Review Time Analytics
Review bottlenecks detected, unreviewed PRs surfaced, reviewer workload balanced, team velocity measured , fix your code review process with data
MCP servers used in this workflow
GitHub
GitHub MCP Server manages repositories, tracks issues, and searches code via AI agents. Connect your GitHub account to your preferred AI client and automate core developer workflows—listing repos, getting file contents, or creating new issues—all from a natural conversation. Manage your entire software development lifecycle without leaving your chat window.
Buildkite
Buildkite MCP Server automates your CI/CD workflow. It lets you manage pipelines, trigger builds, and inspect logs directly through your AI client. Use `list_pipelines` to see all active pipelines, `create_build` to launch tests, and `get_build` to pull specific build details. It gives you full control over builds and agents without opening a terminal or web console.
Notion
Notion MCP Server connects your AI client to the entire Notion workspace. It lets you query structured databases, search pages across titles and content, and read deep into nested document blocks—all through a single API layer. Don't copy-paste data or switch tabs; let your agent act as an intelligent librarian for all your wiki entries and project trackers.