Bryan Thompson
MCP Infrastructure Engineer, Anthropic
I build the pipelines that get plugins to Claude users.
Two of them: the Claude plugin directory and the MCPB desktop-extension pipeline. Build, audit, publish — across six language ecosystems, with drift detection running daily over thousands of listings.
The public trace
Most of this work happens in public repositories, so you don’t have to take my word for any of it. Every number below links to a live GitHub search that recomputes when you open it.
| Repository | Stars | PRs I authored | Merged through the pipeline |
|---|---|---|---|
| anthropics/claude-plugins-official | 33k+ | 210+ | 2,500+ |
| anthropics/knowledge-work-plugins | 23k+ | 50+ | 490+ |
| anthropics/claude-plugins-community | 340+ | 75+ | 2,100+ |
| modelcontextprotocol/mcpb | 2k+ | 10+ | 85+ threads |
| Total | 350+ | 5,000+ |
The 350+ are mine — human-authored engineering changes. The 5,000+ are submissions and rolling updates moving through automation I wrote: each one scanned, validated, and policy-checked before it reaches a merge decision. Building the system was the work; the volume is what it produced.
† The modelcontextprotocol/mcpb row is open-source maintenance — issue and pull request threads participated in — not pipeline throughput, and it is not included in the throughput total. Every figure above is a floor, not an estimate: these counts only grow, and the totals moved by several hundred in the days it took to write this page. Floors verified against the GitHub API on 2026-08-10, and re-checked in CI; each links to a live search that recomputes the exact number when you open it.
Before this: 13 years of reliability engineering on Fortune 500 payment systems at PayPal and Fiserv. That’s where the instinct for staged rollouts and blast-radius containment comes from.
Engineering Solutions That Work in Production
Not theoretical. Not experimental. Production-tested with real users, real money, real uptime.
Live Production Systems
Real Payment Processing
Stripe Integration
- • Webhook processing with 100% reliability
- • PCI-compliant implementation
- • Production error handling
PayPal Systems
- • Subscription management at scale
- • Real-time transaction processing
- • Enterprise security standards
Full-Stack Production Architecture
Frontend
Next.js 15, React 18, TypeScript with 166 production pages
Backend
Node.js, FastAPI, PostgreSQL with enterprise scaling
AI Integration
MCP servers, Vector DBs, Multi-LLM orchestration
MCP Infrastructure & Quality Engineering
Building automation infrastructure and systematic review frameworks that power Claude Desktop's MCP ecosystem
Across four public directory repositories
Nobody does this by hand — that is the point
Into 75+ external repositories
The pipelines
How the build-audit-publish automation is put together: what runs untrusted code and where, what the model is allowed to decide, and what it is never allowed to decide.
The repositories
The public half — MCP servers, assessment tooling and developer tools you can clone and run. Every link checked signed out.