HackerTrans
TopNewTrendsCommentsPastAskShowJobs

re5i5tor

no profile record

comments

re5i5tor
·4 เดือนที่ผ่านมา·discuss
Lots of MCP hate, and some love, in the comments.

80% of MCPs are thin wrappers over APIs . Yes they stink.

A well written remote OAuth MCP need not stink. Tons of advantages starting with strong security baked in.

I like Cloudflare Code Mode as an MCP pattern. Two tools, search and execute.

1M Opus 4.6 also reduces the penalties of MCP’s context approach. Along with tool search etc.
re5i5tor
·4 เดือนที่ผ่านมา·discuss
And people forget, Claude Code isn’t the only Claude surface, and CLIs don’t help in other surfaces other than Cowork.
re5i5tor
·4 เดือนที่ผ่านมา·discuss
Does anyone else see an echo of Severance (Apple TV series) here?
re5i5tor
·5 เดือนที่ผ่านมา·discuss
See my comment above, context-mode has no way to inject itself into the MCP tool-call - response loop.

Still high-value, outside MCPs.
re5i5tor
·5 เดือนที่ผ่านมา·discuss
I dug into this further. Tested empirically and read the code.

Confirmed: context-mode cannot intercept MCP tool responses. The PreToolUse hook (hooks/pretooluse.sh) matches only Bash|Read|Grep|Glob|WebFetch|WebSearch|Task. When I called my obsidian MCP's obsidian_list via MCP, the response went straight into context — zero entries in context-mode's FTS5 database. The web fetches from the same session were all indexed.

The context-mode skill (SKILL.md) actually acknowledges this at lines 71-77 with an "after-the-fact" decision tree for MCP output: if it's already in context, use it directly; if you need to search it again, save to file then index. But that's damage control — the context is already consumed. You can't un-eat those tokens.

The architectural reason: MCP tool responses flow via JSON-RPC directly to the model. There's no PostToolUse hook in Claude Code that could modify or compress a response before it enters context. And you can't call MCP tools from inside a subprocess, so the "run it in a sandbox" pattern doesn't apply.

So the 98% savings are real but scoped to built-in tools and CLI wrappers (curl, gh, kubectl, etc.) — anything replicable in a subprocess. For third-party MCP tools with unique capabilities (Excalidraw rendering, calendar APIs, Obsidian vault access), the MCP author has to apply context-mode's concepts server-side: return compact summaries, store full output queryably, expose drill-down tools. Which is essentially what you suggested above.

Still very high value for the built-in tool side. Just want the boundary to be clear.

Correct any misconceptions please!
re5i5tor
·5 เดือนที่ผ่านมา·discuss
I'm not sure it actually works with MCPs *at all*, trying to get that clarified. How can context-mode get "into the MCP loop"?
re5i5tor
·5 เดือนที่ผ่านมา·discuss
Hmmm. I was talking about the output side. When data comes back from an MCP tool call, context-mode is still not in the loop, not able to help, is it?

Edit: clarify "MCP tool"
re5i5tor
·5 เดือนที่ผ่านมา·discuss
Really intrigued and def will try, thanks for this.

In connecting the dots (and help me make sure I'm connecting them correctly), context-mode _does not address MCP context usage at all_, correct? You are instead suggesting we refactor or eliminate MCP tools, or apply concepts similar to context_mode in our MCPs where possible?

Context-mode is still very high value, even if the answer is "no," just want to make sure I understand. Also interested in your thoughts about the above.

I write a number of MCPs that work across all Claude surfaces; so the usual "CLI!" isn't as viable an answer (though with code execution it sometimes can be) ...

Edit: typo
re5i5tor
·5 เดือนที่ผ่านมา·discuss
I shared a lot of these uninformed (speaking only for myself) opinions, but have a lot more respect for Peter after listening to his recent 3hr interview with Lex Fridman. I came away liking and respecting.
re5i5tor
·5 เดือนที่ผ่านมา·discuss
Slightly off topic but I am writing an Excalidraw MCP that allows Claude Code and Claude.ai to create Excal drawings and then iterate on them — I gave Claude the ability to “see” the resulting drawing via a tool that runs a rendering pipeline and returns a png to the model. It’s producing the Olympic logo pretty nicely ;-)
re5i5tor
·5 เดือนที่ผ่านมา·discuss
Exactly right.
re5i5tor
·5 เดือนที่ผ่านมา·discuss
I strongly recommend against Time Machine to NAS — just mentioned it in an article today as “works great, until it inevitably and catastrophically fails”.

Reliable for me is Kopia from Mac to S3 compatible volume (minio) on Synology.
re5i5tor
·6 เดือนที่ผ่านมา·discuss
Using any plugins or skills for that work?
re5i5tor
·6 เดือนที่ผ่านมา·discuss
Based on a request presumably from a HN viewer, I made the repo [2] for this site public.

[2] https://github.com/cto4ai/cto4ai-blog
re5i5tor
·6 เดือนที่ผ่านมา·discuss
I use Astro deployed on Cloudflare, blog-newsletter kind of site [1], moved over from Hugo. If this keeps Astro viable then it seems like a net win.

[1] https://cto4.ai
re5i5tor
·6 เดือนที่ผ่านมา·discuss
If you aren’t realizing the importance of POSSE imho that’s crazy ;-)
re5i5tor
·6 เดือนที่ผ่านมา·discuss
100% confirm Opus 4.5 is very image smart.
re5i5tor
·6 เดือนที่ผ่านมา·discuss
Am I the only one who thinks (mobile safari with an ad blocker) it’s a jackass move to show a fake popup that leads to “must be an adblocker” and prevents page viewing? Or maybe just bad JS junk causing it?

Update: OMG I turned ad blocker off and what a disaster of a site.
re5i5tor
·7 เดือนที่ผ่านมา·discuss
For anyone using Qwen3-VL: where are you running it? I had tons of reliability problems with Qwen3-VL inference providers on OpenRouter — based on uptime graphs I wasn’t alone. But when it worked, Qwen3-VL was pack-leading good at AI Vision stuff.
re5i5tor
·8 เดือนที่ผ่านมา·discuss
Ha, I have been steeling myself for a long chat with Claude about “how the F to get AI Studio up and working.” With paying being one of the hardest parts.

Without a doubt one essential ingredient will be, “you need a Google Project to do that.” Oh, and it will also definitely require me to Manage My Google Account.