2 points, 1 comments on Hacker News
Source: [Hacker News](https://remote.phyra.ai/)
A single MCP server in front of one service is a solved problem: generate tools from the OpenAPI spec, run it over stdio or HTTP, done. At company scale the problem changes shape. A midsize platform team has forty services, each with its own spec, its own auth, its own staging and production ho...
Connecting an AI agent to internal tools is the first time most teams confront a security boundary that is not enforced by code alone. Traditional programs take instructions from developers and data from users; an LLM-driven agent takes instructions from both , and it cannot reliably tell them a...
My VPS runs a "personal AI agent". It forgets its own abilities every morning. My terminal runs a coding agent.
When a team first wraps an internal platform in MCP, the result almost always looks the same: forty tools named get_x , list_x , create_x , and update_x , plus a few things that should never have been tools at all. The model gets lost, picks the wrong getter, and burns context reading giant resp...
Agent! originally appeared on Hacker News last April. A lot has changed since there.
7 points, 2 comments on Hacker News