Turn a chatbot into a teacher.

Measured with node gen-chatbot-kit.mjs --report, which sizes the generated kit and the live OpenAPI document from the same source. Token counts are the generator’s estimator — characters ÷ 2.8 — not a vendor tokenizer, so treat them as the shape of the bill rather than the invoice. You send one tool shape, not both; the per-turn total is the Anthropic tools plus the prompt.

A ? marks an optional argument. tier is one of primary, middle, high, college, topics; detail is brief, standard (default) or full. Deliberately fewer arguments than the API accepts — every parameter is schema bytes on every turn, and a teaching bot has no use for cursors, formats or export options.

export SCOLAVO_TOKEN="$(curl -s "https://scolavo-auth.auth.us-east-1.amazoncognito.com/oauth2/token" \
  -u "$CLIENT_ID:$CLIENT_SECRET" \
  --data-urlencode 'grant_type=client_credentials' \
  --data-urlencode 'scope=scolavo-mcp/content.read' | jq -r .access_token)"

content.read is the only scope the chatbot surface needs. Do not grant the bot content.export or media.download — a scope a bot cannot use is a scope it cannot be talked into using.

import Anthropic from '@anthropic-ai/sdk'
import { createClient } from './chatbot-kit/adapter.mjs'

const scolavo = createClient({
  baseUrl: 'https://mcp.scolavo.com',
  token: process.env.SCOLAVO_TOKEN,
})
const anthropic = new Anthropic()

async function chat(messages) {
  for (;;) {
    const res = await anthropic.messages.create({
      model: 'claude-sonnet-5',
      max_tokens: 2048,
      system: [{ type: 'text', text: scolavo.systemPrompt, cache_control: { type: 'ephemeral' } }],
      tools: scolavo.tools,
      messages,
    })
    messages.push({ role: 'assistant', content: res.content })

    const calls = res.content.filter((c) => c.type === 'tool_use')
    if (!calls.length) return res

    const results = await Promise.all(calls.map(async (c) => {
      const out = await scolavo.call(c.name, c.input)
      return { type: 'tool_result', tool_use_id: c.id, content: out.text, is_error: out.isError }
    }))
    messages.push({ role: 'user', content: results })
  }
}

The cache_control marker is the part not to skip: it makes the system prompt a cached prefix, so most of the per-turn overhead is billed at a fraction of the input rate on every turn after the first. Keep the prompt byte-stable across requests, or the cache misses and you pay full price every time.

import OpenAI from 'openai'
import { createClient } from './chatbot-kit/adapter.mjs'

const scolavo = createClient({ baseUrl: 'https://mcp.scolavo.com', token: process.env.SCOLAVO_TOKEN })
const openai = new OpenAI()

async function chat(messages) {
  for (;;) {
    const res = await openai.chat.completions.create({
      model: 'gpt-4.1',
      messages: [{ role: 'system', content: scolavo.systemPrompt }, ...messages],
      tools: scolavo.toolsOpenAI,
    })
    const msg = res.choices[0].message
    messages.push(msg)
    if (!msg.tool_calls?.length) return msg

    for (const c of msg.tool_calls) {
      const out = await scolavo.call(c.function.name, JSON.parse(c.function.arguments))
      messages.push({ role: 'tool', tool_call_id: c.id, content: out.text })
    }
  }
}

TIER_NOT_LICENSED: No grant covers this content tier.
This licence does not cover that tier. Tell the learner it is outside what you can teach,
and offer something list_subjects does cover.

Download the guide .md ↓