Moshe Avdiel

Posted on Sep 11 Originally published at github.com

MCP host Finished the Turn Blind — Admin wall tile without SPA tokens on the Senses Path

I have sat next to the senses wall at 00:40 while MCP host was this close to doing the wrong thing.

Not a model failure. A posture failure.

The host had started with wall-focus frozen in env / argv / a skill file. Someone on the floor said, out loud, priority is a leaf, not a restart. MCP host was still holding the old process. The only “safe” move anyone trusted was:

Kill MCP host (or its MCP server)
Edit a file
Restart the host
Lose the turn budget and the open investigation

I have watched that restart more times than I want to admit. It feels responsible. It is a ceremony. a mid-turn interrupt the host treats as noise does not wait for ceremonies.

The Aha: Admin wall tile without SPA tokens is not a binary you reboot. It is a function that should read live posture from Kiponos.io on every call. The host stays up. The leaf moves.

The problem: Admin wall tile without SPA tokens lived in the process, not in the turn

MCP host is good at calling tools. It is not born with a shared, instant, restart-free control plane.

So teams hide Admin wall tile without SPA tokens in the only places agent frameworks actually ship:

Where the gate hid	What you restart	What you lose
MCP server env / argv	The MCP process	Open tool sessions
Skill file on disk	The agent turn, sometimes the host	Context the model already paid for
Host-local JSON	Whatever still has the file open	Agreement between two agents
Hard-coded `if` on `wall-focus`	A release	The incident clock

The senses wall already knew. MCP host did not, because it had started earlier.

That is the missing piece: the framework gave you tools. It did not give you a live hub.

What teams believe

Belief	Production
We'll catch it next turn	The senses wall already knew this turn
Restart MCP host — it is cheap	Cheap until 00:40 ate the turn budget and the open investigation
The skill file is the source of truth	Skills instruct. They do not fan out
Put the SDK in the SPA	Connect tokens do not belong in a browser

The Aha: local get, live write, host stays up

Kiponos holds a nested tree. Java and Python SDKs keep the latest values in memory, patched over WebSocket deltas. The hot path inside a MCP host tool is a local get — no HTTP RTT per senses lookup.

Hub leaf for this essay:

examples/agentic-dev-1102-am-admin-wall/wall-focus = live

Runnable proof: examples/java/agentic-dev-1102-am-admin-wall

Public SDKs: Java, Python, plus React/Angular server peers (createFromEnv). Never put Connect tokens in the SPA.

Config tree (senses + peers)

examples/
  agentic-dev-1102-am-admin-wall/
    wall-focus: live          # Admin wall tile without SPA tokens
apps/
  senses/
    live:
      wall-focus: live

Integration — Java hot path

Kiponos kip = Kiponos.createForCurrentTeam();
Folder gate = kip.getRootFolder()
        .folderOrCreate("examples")
        .folderOrCreate("agentic-dev-1102-am-admin-wall");
if (!gate.hasKey("wall-focus")) {
    gate.set("wall-focus", "live");
}
String posture = gate.get("wall-focus");
// MCP host tool: refuse the dangerous call when posture moved

Same leaf from a Python tool (MCP host just calls it):

from kiponos import Kiponos

k = Kiponos.connect(quiet=True)  # env: KIPONOS_ID, KIPONOS_ACCESS, KIPONOS
try:
    posture = k.get("examples/agentic-dev-1102-am-admin-wall/wall-focus", "live")
    if str(posture) == "live":
        raise PermissionError("Admin wall tile without SPA tokens gated live — host not restarted")
finally:
    k.disconnect()

The MCP host process does not recycle. The next tool call already sees the dashboard edit.

Real scenarios

Event	Without Kiponos	With Kiponos
A mid-turn interrupt the host treats as noise	Restart MCP host; lose the turn budget and the open investigation	Set `wall-focus` live; next MCP host tool call already obeys
Peer host still on old wall-focus	Paste the value into the other chat	One hub leaf; both processes `get()` locally
senses wall shows the new posture	MCP host started earlier so it writes anyway	Dashboard and tool share the same memory tree
Incident over, resume	Another MCP host restart	Set `wall-focus` back; session continues
Mirror phone already showing the new device leaf	Two ceremonies, two lost threads	Same tree, two products, no paste

Performance (this path, not a generic table)

MCP host tool get() is an in-process map lookup after bootstrap.
One WebSocket per process lifetime — not per senses line.
A dashboard edit is a delta of wall-focus, not a config-file reload.
You do not pay model tokens to “please restart MCP host.”
A second host converges without a third paste onto mirror phone already showing the new device leaf.

Compare to alternatives

Approach	Honest fit	Why it still restarts
Env file + MCP host reboot	Simple at 09:00	The freeze is at 00:40
Skill markdown as policy	Good instructions	Not a live bus
Redis poll inside the tool	Shared, but RTT on the hot path	You invented a hub with worse UX
Feature-flag SaaS	Product experiments	Rarely session-safe for MCP host
`@RefreshScope` / actuator	JVM apps	Does not restart MCP host

When not to use Kiponos

Situation	Why
Tool schema itself changed (new argument)	That is a code/MCP host restart
Secret rotation of Connect tokens	Credentials are not live knobs
One-off local script, no peers	A hub is overkill
Browser-only “SDK in the SPA”	Forbidden — tokens leak or defaults lie

Rehearsal beats slides

In staging: set a painful wall-focus, prove MCP host recovers without a host kill, prove clamps reject nonsense, prove last-known-good when the hub is firewalled. That drill ends half the architecture arguments about Admin wall tile without SPA tokens.

Why MCP host is the wrong restart target

MCP host is good at calling tools. It is not a control plane. Killing it to flip wall-focus teaches the on-call that judgment requires a process ID. The senses wall already disagrees.

What the senses operator actually said

At 00:40 someone said, out loud: priority is a leaf, not a restart. That sentence is the whole product. If it cannot land in the running MCP host process in seconds, you do not have posture. You have a wiki.

Getting started (15 minutes)

TeamPro on kiponos.io → Connect → KIPONOS_ID / KIPONOS_ACCESS / profile ['my-app']['v1.0.0']['dev']['base'].
Clone github.com/kiponos-io/kiponos-io.
cd examples/java/agentic-dev-1102-am-admin-wall && cp kiponos.local.env.example kiponos.local.env
./gradlew test run — prints examples/agentic-dev-1102-am-admin-wall/wall-focus=...
In the dashboard, change wall-focus. Keep the process up. No rebuild.
Point your MCP host tool at the same leaf. Do not ship a new server binary to flip Admin wall tile without SPA tokens.

The moral

If flipping Admin wall tile without SPA tokens requires restarting MCP host, you do not have a gate. You have a hope with a process ID.

Agent frameworks already know how to call tools. Kiponos is the live hub they do not ship — so the senses wall can change its mind without killing the session.

How to try: examples/java/agentic-dev-1102-am-admin-wall and ./gradlew test.

DEV Community