Most MCP servers just wrap CRUD JSON APIs into tools — I did it too with scim-mcp and garmin-mcp-app. It works, until you realize a tool call dumps 50KB+ into context.
MCP isn't dead — but we need to design MCP tools with the context window in mind.
Most MCP servers just wrap CRUD JSON APIs into tools — I did it too with scim-mcp and garmin-mcp-app. It works, until you realize a tool call dumps 50KB+ into context.
MCP isn't dead — but we need to design MCP tools with the context window in mind.
Note
This does not works in browser for quests which require you to play a game! Use the desktop app to complete those.
How to use this script:
Console tab| [ | |
| { | |
| "flag": "https://twemoji.maxcdn.com/2/svg/1f1e6-1f1e8.svg", | |
| "country": "Ascension Island", | |
| "code": "ac" | |
| }, | |
| { | |
| "flag": "https://twemoji.maxcdn.com/2/svg/1f1e6-1f1e9.svg", | |
| "country": "Andorra", | |
| "code": "ad" |
Companion prompts for the video: OpenClaw after 50 days: 20 real workflows (honest review)
These are the actual prompts I use for each use case shown in the video. Copy-paste them into your agent and adjust for your setup. Most will work as-is or the agent will ask you clarifying questions.
Each prompt describes the intent clearly enough that the agent can figure out the implementation details. You don't need to hand-hold it through every step.
My setup: OpenClaw running on a VPS, Discord as primary interface (separate channels per workflow), Obsidian for notes (markdown-first), Coolify for self-hosted services.
| name: Security audit | |
| on: | |
| schedule: | |
| - cron: '0 0 * * *' | |
| push: | |
| paths: | |
| - '**/Cargo.toml' | |
| - '**/Cargo.lock' | |
| jobs: | |
| security_audit: |
/* 前言 -------------------------------------------------- */
這是 Jeremy 於 2026-03-07 於第二屆「 AI 取暖會」中分享過去十八個月來與 AI/Agent 搏鬥的實戰心得。