16 posts tagged #mcp-servers.
The loop engineering parts list from June 2026, classified by one question: five blocks are context moves, one is a schedule, and the genre's signature failure is fixed by a seventh block the list never counted.
A vibe-coded Stripe integration buries nine decisions in one handler. A teaching clause plus a plan-mode gate surfaces all nine - only three are worth your own trip to the docs.
destructiveHint plus elicitation gates a destructive MCP tool for clients that declare elicitation; for the rest, the fallback you write is the whole guarantee.
The MCP spec hands a server three levers: resources for the application, tools for the model, prompts for the user. Skip that sort and your reads ride the tool list every turn, at a price you can compute.
When a required tool parameter is a fact only the human holds, the two familiar responses, fail and guess, each cost one round trip on the wire and guarantee nothing. Under the MCP spec current since 2026-07-28, asking costs exactly two round trips, fixed, whatever the human answers.
Ask an agent to grade the work you just described and it grades the paragraph, not the code, because agreeing with a confident claim is the model's strongest reflex. Hand the same model the live diff and a rubric you author, and it finds the four misses your summary hid.
A confidently wrong answer is two bugs in one costume: a fact that never reached the context window, and a fact that arrived and got ignored. Log the window, score two binaries, and each bug routes to a different layer of the stack.
A 20-issue Sentry triage sweep run inline leaves 21,000 tokens of tool exhaust in the main thread. Dispatched to a subagent under a three-line return contract, it leaves 60. The ratio holds at every cadence.
The GitHub MCP server that leaked private repo names in May 2025 had no malicious code in it. The token's authority was ambient, good for every repo you can see. Scope it to the task and the blast radius drops 12x.
A raw token passthrough hands an injected agent all 34 endpoints of your billing API, five of them destructive. Hold the token server-side and expose three curated verbs instead: one bounded write, capped at $500 a call and logged.
A model has one procedure for turning tool bytes into a sentence, so a clean success and a swallowed failure read the same. On 12 refund calls, narration confirms 3 that never happened; a validated output schema confirms zero.
The triage prompt your team keeps re-typing makes the agent reassemble, through three round trips, context one expert already knew how to assemble once. That costs 600 plumbing tokens and 7.2 seconds per run. A server-side MCP prompt pays the assembly once, for everybody.
The model cannot tell an instruction from data, because both arrive as tokens in one flat stream. The defense that measured best marks which channel a token came from. It never reads the words.
A team wiring three agent surfaces to three systems by hand pays for nine adapters, 108 hours of year-one work. One MCP server per system, pointed at from each agent, costs 40.5 hours, and the ratio climbs with every agent the team adds.
Task selection is the one decision still routing every ticket through you. Write the priority order down once, and the 80 touches a sprint costs you collapse to 1 - same agent, same backlog.
MCP is the standard protocol for plugging external systems - issue trackers, databases, design tools - into AI agents. Here's what changes when you use it.