The Protobox Blog
Notes from building, hosting, and scaling MCP servers in production. Practical writing for developers.
Latest articles
Dev NotesHow to manage a hosted MCP server from the terminal
Every dashboard click is an ops task you cannot script. Run your hosted MCP server from the terminal instead: tools, toolsets, keys, knowledge, and CI.
Security & Compliance71% of organizations aren't prepared to secure their AI agents' tools
MCP gives AI agents autonomous access to real systems — and introduces attack vectors that traditional security can't see. A technical breakdown of tool poisoning, rug pulls, cross-server shadowing, and the defense framework production teams need now.
All articles
42 articles · Page 1 of 4
How to manage a hosted MCP server from the terminal
Every dashboard click is an ops task you cannot script. Run your hosted MCP server from the terminal instead: tools, toolsets, keys, knowledge, and CI.
71% of organizations aren't prepared to secure their AI agents' tools
MCP gives AI agents autonomous access to real systems — and introduces attack vectors that traditional security can't see. A technical breakdown of tool poisoning, rug pulls, cross-server shadowing, and the defense framework production teams need now.
How to register MCP tools without running a server
Hand-rolling an MCP server means owning transport, auth, hosting, and schema drift. Registering the same tools against a hosted MCP endpoint skips all four.
MCP Servers in Production: Observability from Day One
Instrument your MCP servers with OpenTelemetry for production-grade observability. Covers tracing tool calls, detecting loops, cost attribution, and alerting.
How Much Testing Is Enough for Your AI Agent?
Code coverage doesn't apply to AI agents. Here's a framework for thinking about evaluation coverage: how many scenarios you need, what distribution to target, and how to know when you've tested enough.
Your Agent Aced the Benchmark. Production Disagreed.
We scored 92% on GAIA. Production failed the same scenarios 25% of the time. Here's which AI agent benchmarks actually predict deployed performance, why most don't, and what to measure instead.
Agent Drift: Why Your AI Gets Worse the Longer It Runs
AI agents silently degrade over long conversations. Research quantifies three types of drift and shows why point-in-time evals miss them entirely.
MCP now uses round-trips, not streams, for user input
The July 28 spec deprecated elicitation and sampling. Multi Round-Trip Requests (SEP-2322) replace both with a stateless pattern: the server returns InputRequiredResult, the client collects input, the client re-submits. Here's how to migrate.
7 FastMCP mistakes that break your agent in production
FastMCP servers that work locally often fail at scale. Seven common mistakes, from missing annotations to monolithic tool sets, and how to fix each one.
MCP SSE Is Deprecated. Here's How to Migrate
SSE transport is being deprecated across major MCP platforms in 2026. Here's a practical migration guide from HTTP+SSE to Streamable HTTP, with TypeScript examples and a phased rollout strategy.
The Tool Explosion: Managing 50+ Agent Tools Without Losing Your Mind
As agents get more capable, tool sprawl becomes a real operational problem. Here's how to organize, test, and monitor function calling at scale before it breaks in production.
Your MCP server is a monolith. Here's how to fix it
MCP servers dump every tool into the context window, burning tokens before your agent reasons. Four patterns to fix it: decompose, filter, gateway, facade.
MCP changelog and dev notes
Short, occasional updates on the MCP spec, new Protobox features, and patterns we've seen in production. No marketing fluff.
