Which integrations are available for this server?

Provides prompt optimization for models like ChatGPT, improving clarity and structure.

How do I use Nümtema Prompt Optimizer MCP?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Nümtema Prompt Optimizer MCP Optimize my draft prompt: Create a SaaS landing page." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Nümtema Prompt Optimizer MCP

by Creativityliberty

Overview Schema Related Servers Score Discussions

JavaScript

Remote

Nümtema Prompt Optimizer MCP

A minimal, open-source MCP server that turns a rough prompt into a clearer, structured prompt.

One tool: optimize_prompt
Zero runtime dependencies
No API key
No database or prompt storage
No OAuth or widget in this MVP
Stateless Streamable HTTP endpoint for ChatGPT

What the tool returns

{
  "optimized_prompt": "...",
  "improvements": ["..."],
  "missing_information": ["..."],
  "assumptions": ["..."],
  "score_before": 30,
  "score_after": 87,
  "mode": "balanced",
  "target_model": "chatgpt",
  "language": "fr"
}

The engine is deterministic. It does not call an LLM and never silently invents missing project facts. Missing details are exposed as placeholders.

Related MCP server: json-promptor-mcp

Requirements

Node.js 20 or newer

No npm install is necessary because the server has no dependencies.

Run locally

npm start

Default endpoints:

http://127.0.0.1:3000/health
http://127.0.0.1:3000/mcp

Development mode:

npm run dev

Test

npm test
npm run check

Quick protocol smoke test

Initialize:

curl -s http://127.0.0.1:3000/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{
    "jsonrpc":"2.0",
    "id":1,
    "method":"initialize",
    "params":{
      "protocolVersion":"2025-11-25",
      "capabilities":{},
      "clientInfo":{"name":"curl","version":"1.0.0"}
    }
  }'

List tools:

curl -s http://127.0.0.1:3000/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -H 'MCP-Protocol-Version: 2025-11-25' \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}'

Call the optimizer:

curl -s http://127.0.0.1:3000/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -H 'MCP-Protocol-Version: 2025-11-25' \
  -d '{
    "jsonrpc":"2.0",
    "id":3,
    "method":"tools/call",
    "params":{
      "name":"optimize_prompt",
      "arguments":{
        "prompt":"Crée-moi un site pour vendre des ebooks",
        "mode":"balanced",
        "target_model":"chatgpt"
      }
    }
  }'

Connect it to ChatGPT

ChatGPT needs a reachable HTTPS /mcp endpoint.

Run the server locally with npm start.
Expose port 3000 through the OpenAI Secure MCP Tunnel, Cloudflare Tunnel, ngrok, or deploy the Docker image to an HTTPS host.
In ChatGPT, enable Developer Mode under Settings → Security and login.
Open Settings → Plugins, create a developer-mode app, and enter:

Name: Nümtema Prompt Optimizer
Description: Improves rough prompts, identifies missing information, and returns a reusable structured prompt.
MCP server URL: https://YOUR-DOMAIN.example/mcp

Create a new conversation, enable the app from the composer, and ask:

Optimise ce prompt avec Nümtema Prompt Optimizer :
Crée-moi un site moderne pour vendre des ebooks sur l'intelligence artificielle.

When tool metadata changes, refresh the developer app from ChatGPT settings.

Tool inputs

Field	Required	Default	Description
`prompt`	yes	—	Raw prompt, 3–20,000 characters
`mode`	no	`balanced`	`fast`, `balanced`, or `deep`
`target_model`	no	`chatgpt`	Target assistant/model family
`language`	no	`auto`	`auto`, `fr`, or `en`
`context`	no	—	Project or situation context
`audience`	no	—	Intended audience
`output_format`	no	—	Required response format

Configuration

HOST=127.0.0.1
PORT=3000
ALLOWED_ORIGINS=https://chatgpt.com,https://www.chatgpt.com,https://chat.openai.com

Set HOST=0.0.0.0 inside containers. ALLOWED_ORIGINS=* is available for controlled testing but is not recommended for production.

Docker

docker build -t numtema-prompt-optimizer-mcp .
docker run --rm -p 3000:3000 numtema-prompt-optimizer-mcp

Deliberate MVP limits

This version does not include user accounts, history, profiles, OAuth, UI widgets, billing, async jobs, provider APIs, or multi-agent orchestration. Those belong in later versions only after this single tool proves useful.

License

MIT

This server cannot be installed

license - permissive license

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Creativityliberty/mcptest1'

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