Track Technical Debt Per Pull Request via MCP.
Build failures analyzed, code complexity measured, tech debt cataloged, remediation prioritized , track what you owe your codebase
Works with every AI agent you already use
…and any MCP-compatible client
Waiting for input…
Gemini How It Works
Your AI agent reads CircleCI: the `lint` step is failing 18% of the time across all pipelines , that is not flaky, that is a code quality problem.
The `test` step takes 12 minutes on average for `api-server` but only 4 minutes for `web-app` , the api-server test suite is 3x slower relative to codebase size.
The agent searches GitHub: 47 TODO comments across the codebase, 12 marked `// TODO: HACK` or `// FIXME`. It finds 8 files over 500 lines long.
It finds 3 deprecated dependencies flagged in package.json audit. It reads open issues labeled 'tech-debt' , 15 issues, 9 unassigned.
The agent creates Airtable records: 'DEBT-001: 47 TODO comments (12 critical hacks). Effort: 2 sprints. Priority: Medium.' 'DEBT-002: api-server test suite 3x slower than expected.
Effort: 1 sprint. Priority: High.' 'DEBT-003: 8 files over 500 lines need refactoring. Effort: 3 sprints. Priority: Low.' 'DEBT-004: 3 deprecated dependencies.
Effort: 1 week. Priority: High (security).' The Airtable board becomes the team's tech debt register , sortable by priority, filterable by service, trackable over time.
MCP Server Orchestration: 3 MCP Servers, one intelligent agent
Connect CircleCI, GitHub and Airtable MCP servers so your AI agent analyzes CI pipeline failures, reads code quality signals from your repositories (TODOs, deprecated patterns, long files, missing tests), catalogs them as tech debt items in Airtable with severity and estimated effort, and tracks remediation over time. Engineering teams who know they have tech debt but never quantify it get a living inventory that grows and shrinks as the codebase evolves. No spreadsheet maintained by hand. No tech debt retro that produces a list nobody looks at. One prompt and your debt register is current.
Circleci
triggerReads pipeline failures, workflow durations and job details
list_cci_pipelines list_pipeline_workflows list_workflow_jobs get_job_details Github
actionScans code for TODOs, deprecated patterns and quality signals
search_github_code get_file_contents list_repo_issues get_repository_details Airtable
actionMaintains a tech debt inventory with severity and remediation tracking
create_records list_records get_record list_bases 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.
- Circleci, Github & Airtable 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 who know they have tech debt but have never quantified it in a trackable format
CTOs preparing for engineering investment conversations who need a prioritized debt inventory with effort estimates
Tech leads who want automated detection of code quality regressions , growing TODO counts, slowing test suites, rising lint failure rates
Teams adopting tech debt sprints who need a prioritized backlog of debt items to work from
Frequently Asked Questions About This MCP Server Orchestration
Which MCP servers do I need for this workflow?
Three: CircleCI, GitHub and Airtable. Connect all three to your AI client.
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.
Can I use Buildkite instead of CircleCI?
Yes. Replace the CircleCI MCP server with the Buildkite MCP server. The agent reads pipeline and job data the same way.
How accurate are the effort estimates?
Effort estimates are T-shirt sized based on the scope of the debt item. They serve as planning guidelines, not commitments. Adjust based on your team's velocity.
Can I use Linear or Jira to track debt instead of Airtable?
Yes. Replace Airtable with Linear or Jira. The agent creates issues/tickets instead of Airtable records.
How often should I run the audit?
Monthly is ideal for trend tracking. Quarterly is the minimum for meaningful debt management. Weekly is too frequent , debt does not change that fast.
MCP Servers That Diagnose CI Failures First
Your CI pipeline has been red for 6 hours and the team keeps pushing to the same branch , nobody knows the failure is a flaky infrastructure test, not their code
Track Engineering Metrics Using MCP Servers
Merge request velocity measured, pipeline success rates tracked, cycle time calculated, team metrics published , build your DORA dashboard without a BI tool
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
MCP servers used in this workflow
CircleCI
CircleCI MCP Server lets your AI agent manage your entire CI/CD lifecycle. Use it to list recent pipelines, check job statuses, trigger new builds, and audit project workflows without opening the CircleCI dashboard. It gives you full control over your software delivery process directly from your chat client.
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.
Airtable
Airtable connects your structured data bases to your AI agent. Use it to query records, read schemas, update spreadsheets, and build automated workflows directly through chat. You can list bases, query specific records, or bulk-add data without leaving your chat client.