Schema | KAI Work Host

KAI Work Host

Describes the environment variables required to run the server.

Name	Required	Description	Default
`KAI_WORK_HOST_HOME`	No	獨立 runtime root；部署器會改成 instance-specific root	%LOCALAPPDATA%\KAI\WorkHost
`KAI_WORK_HOST_DSH_HOME`	No	Profile／Session／OAuth grant	<HOME>\dsh
`KAI_WORK_HOST_DSH_ROOT`	No	唯讀 DSH checkout	<HOME>\dependencies\<exact-pin>
`KAI_WORK_HOST_BEARER_TOKEN`	No	非 loopback HTTP bind 必填
`KAI_WORK_HOST_DSH_PROVIDER`	No	固定 Luna 訂閱 route	openai-codex
`KAI_WORK_HOST_WORKER_MODEL`	No	預設 worker model；WebGPT 每回合仍可選 Luna-family model	gpt-5.6-luna
`KAI_WORK_HOST_CONTEXT_CHARS`	No	第一輪完整 context capsule 上限；fast=true 時壓到最多 8000	12000
`KAI_WORK_HOST_WORKER_EFFORT`	No	預設 reasoning effort，也是 WebGPT 每回合可選 effort 的上限	high
`KAI_WORK_HOST_EXECUTION_PROFILE`	No	預設 fast mode 來源；另有 standard	lean

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/paul800901/kai-work-host'

If you have feedback or need assistance with the MCP directory API, please join our Discord server