ProtoboxProtobox

El Blog de Protobox

Notas sobre construir, hostear y escalar servidores MCP en producción. Escritura práctica para desarrolladores.

Todos los artículos

42 artículos · Página 1 de 4

Warm watercolor illustration of a person connecting modular components and cables at a warm sunlit workbench
Dev Notes·11 min de lectura

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.

Leer más
Warm watercolor illustration of a person examining lock mechanisms and inspection tools under warm amber light
Security & Compliance·16 min de lectura

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.

Leer más
Warm watercolor illustration of a person connecting modular components and cables at a warm sunlit workbench
Dev Notes·10 min de lectura

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.

Leer más
Warm watercolor illustration of a person watching a wall of softly glowing displays tracking patterns
Production MCP·20 min de lectura

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.

Leer más
Warm watercolor illustration of a person reviewing clipboards of scores and comparison cards in a bright glass-walled room
Testing & Evaluation·13 min de lectura

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.

Leer más
Warm watercolor illustration of a person reviewing clipboards of scores and comparison cards in a bright glass-walled room
Testing & Evaluation·13 min de lectura

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.

Leer más
Warm watercolor illustration of a person reviewing clipboards of scores and comparison cards in a bright glass-walled room
Testing & Evaluation·14 min de lectura

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.

Leer más
Warm watercolor illustration of an MCP client and server exchanging a request, a paused input form, and a re-submitted call in a loop
Protocol Deep Dives·14 min de lectura

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.

Leer más
Warm watercolor illustration of a person reviewing clipboards of scores and comparison cards in a bright glass-walled room
Production MCP·14 min de lectura

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.

Leer más
Warm watercolor illustration of a person watching flowing streams of light on a live display
Protocol Deep Dives·12 min de lectura

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.

Leer más
Warm watercolor illustration of a person connecting modular components and cables at a warm sunlit workbench
Tools & MCP·14 min de lectura

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.

Leer más
Warm watercolor illustration of a person connecting modular components and cables at a warm sunlit workbench
Agent Architecture·14 min de lectura

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.

Leer más

Changelog MCP y notas para devs

Actualizaciones cortas y ocasionales sobre la spec MCP, nuevas funciones de Protobox y patrones que vemos en producción. Sin marketing innecesario.

Sé de los primeros