About mcp
mcp is an MCP server published by git+prompt-template in the AI category: model Context Protocol @prompt-template adapter.
Install
Install
npx @prompt-template/mcpClaude Code
claude mcp add prompt-template -- npx -y @prompt-template/mcpnpx
npx -y @prompt-template/mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
✦
Ask AI about mcp
Powered by Claude · Grounded in docs
I know everything about mcp. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
- ✓README presentThe repository ships documentation.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
4 checks have not been run yet.
README
@prompt-template
Monorepo for the core @prompt-template modules, types, and adapters.
Quick start
npm i @prompt-template/core
import { PromptTemplate } from '@prompt-template/core'
const promptTemplate = PromptTemplate.create`
Brainstorm 3 names for a superhero ${'animal'}.
`
const prompt = promptTemplate.format({
animal: 'cat',
})
//=> 'Brainstorm 3 names for a superhero cat.'
For detailed usage and API documentation, please refer to the README in packages/core.
With OpenAI
npm i @prompt-template/core @prompt-template/openai openai
import { PromptTemplate } from '@prompt-template/core'
import { ChatPromptTemplate } from '@prompt-template/openai'
import { OpenAI } from 'openai'
const chatPromptTemplate = ChatPromptTemplate.from([
{
role: 'system',
content: 'You are a friendly assistant.',
},
{
role: 'user',
promptTemplate: PromptTemplate.create`
Brainstorm 3 names for a superhero ${'animal'}.
`,
},
])
const messages = chatPromptTemplate.format({
animal: 'cat',
})
//=> [
// { role: 'system', content: 'You are a friendly assistant.' },
// { role: 'user', content: 'Brainstorm 3 names for a superhero cat.' }
// ]
const openai = new OpenAI()
const completion = await openai.chat.completions.create({
model: 'gpt-4o-mini',
messages,
})
console.log(completion.choices[0]?.message.content)
For detailed usage and API documentation, please refer to the README in packages/openai.
With AI SDK
npm i @prompt-template/core @prompt-template/ai-sdk @ai-sdk/openai ai
import { PromptTemplate } from '@prompt-template/core'
import { ChatPromptTemplate } from '@prompt-template/ai-sdk'
import { openai } from '@ai-sdk/openai'
import { generateText } from 'ai'
const chatPromptTemplate = ChatPromptTemplate.from([
{
role: 'system',
content: 'You are a friendly assistant.',
},
{
role: 'user',
promptTemplate: PromptTemplate.create`
Brainstorm 3 names for a superhero ${'animal'}.
`,
},
])
const messages = chatPromptTemplate.format({
animal: 'cat',
})
//=> [
// { role: 'system', content: 'You are a friendly assistant.' },
// { role: 'user', content: 'Brainstorm 3 names for a superhero cat.' }
// ]
const completion = await generateText(openai, {
model: openai('gpt-4o-mini'),
messages,
})
console.log(completion.text)
README copy captured when this server was indexed; it may lag the repository. The original is authoritative.