Menu

Post image 1
Post image 2
1 / 2
0

3 MCP server failure modes that bit us in production, and how we ship around them

DEV Community·Takayuki Kawazoe·about 1 month ago
#PuEqBKIg
#failure#comment#mcp#claude#agent#server
Reading 0:00
15s threshold

MCP feels easy until it isn't. The first time you wire up a stdio server and call a tool from a Claude Agent SDK loop, the whole thing fits on a slide. Then you put it in front of customer codebases, customer GitHub credentials, customer build containers, and the sharp edges show up in places the spec is silent on. Tools start shadowing each other. The agent confidently uses a built-in Read when you wanted it to go through your sandboxed file server. Environment variables you set on the parent process reappear inside the MCP child and become tokens-in-prompts. I'm building a SaaS that uses MCP heavily across a few different services (Codens, an AI dev harness with several specialized agents — happy to talk about it but it isn't the point of this post). Across those services we have GitHub MCPs for repo reads, an in-process Playwright MCP for browser exploration, and per-workspace local-file MCPs that let an agent navigate a cloned repo without escaping the sandbox.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Read More