re5i5tor

I have journeyed from Claude Code to OMP to Pi while working very hard to keep a super open mind, open to anything.

This from the post is why I landed on Pi

"What makes Pi the best fit here? Simple: it’s the only harness today that’s open source, vendor-agnostic, extensible, and minimal enough to not force opinions on you. It gives you full ownership and puts you in control. Being able to change the providers without switching apps alone is reason enough to adopt it, but the fact that it’s also so flexible makes it almost impossible for me to switch back."

I am building my own (intentionally simple) subagent orchestration framework inside Pi and am watching Pi Durable closely as I suspect it and Pi will unify before long and subagents are better supported in Durable. (Relatively uninformed opinion in this case, not using Durable yet.)

Edit-typo

“caveats and provisos” makes me think of Robin Williams’ genie imitating William F. Buckley Jr.

Have you tried it? I’d recommend doing so, it’s impressive in real use cases.

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.

And people forget, Claude Code isn’t the only Claude surface, and CLIs don’t help in other surfaces other than Cowork.

Does anyone else see an echo of Severance (Apple TV series) here?

See my comment above, context-mode has no way to inject itself into the MCP tool-call - response loop.

Still high-value, outside MCPs.

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!

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"?

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"

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

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.

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 ;-)

Exactly right.

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.