DEV Community

Cover image for PromptOT MCP: Manage and version LLM prompts from your AI tools
PromptOT
PromptOT

Posted on

PromptOT MCP: Manage and version LLM prompts from your AI tools

#claude #mcp #productivity #tutorial

PromptOT MCP: Manage and version LLM prompts from your AI tools

Prompts often start as simple strings in code.

Then the product grows.

You add a better system prompt. Then a guardrail. Then a different version for production. Then a customer-specific variable. Then test cases. Then someone wants to roll back to the version from last week.

At that point, prompts are no longer just text. They become part of the application layer.

That is the problem PromptOT is built around.

PromptOT is a prompt management platform for LLM applications. It lets teams build, version, evaluate, and deliver system prompts through an API without redeploying the app every time a prompt changes.

The new part I want to share is the PromptOT MCP server.

It lets you manage your PromptOT prompts directly from MCP-compatible AI tools like Claude Desktop, Cursor, Codex, ChatGPT, claude.ai, and other clients.

What is MCP?

MCP stands for Model Context Protocol.

It gives AI tools a standard way to connect with external systems. Instead of only chatting with an assistant, you can give the assistant controlled tools for reading and changing real application data.

For PromptOT, that means your AI assistant can help with things like:

  • listing prompts
  • editing prompt blocks
  • managing variables
  • saving drafts
  • publishing versions
  • rolling back versions
  • creating test cases
  • comparing prompt versions

The goal is not just to generate prompt text. The goal is to manage prompt operations as part of the development workflow.

What PromptOT does

PromptOT lets you structure prompts as versioned assets instead of hardcoded strings.

A prompt can be composed from typed blocks, such as:

  • role
  • context
  • instructions
  • guardrails
  • output format

It also supports variables like:

{{customer_name}}
{{tone}}
{{product_context}}
Enter fullscreen mode Exit fullscreen mode

Those variables can be resolved when your application fetches the prompt.

So instead of redeploying your app every time you adjust a prompt, your app can fetch the latest published prompt through an API.

What the MCP server adds

The PromptOT MCP server exposes 23 tools across five areas:

Area What you can do
Prompts List, get, compile, create, update, and delete prompts
Blocks Create, edit, delete, and reorder typed prompt blocks
Variables Manage {{key}} placeholders
Versions Save drafts, publish, diff, and roll back
Test cases Create and manage prompt evaluation inputs

That makes it possible to work on prompts from inside the AI tools developers already use.

For example, you can ask your assistant to:

Show me the current support-agent prompt.
Enter fullscreen mode Exit fullscreen mode

Then:

Add a stricter refund-policy guardrail as a new block, but save it as a draft.
Enter fullscreen mode Exit fullscreen mode

Then:

Compare this draft with the currently published version.
Enter fullscreen mode Exit fullscreen mode

Then:

Publish the draft if the changes look safe.
Enter fullscreen mode Exit fullscreen mode

The assistant is not just writing text in a chat window. It is using scoped PromptOT tools to work with real prompt objects.

Installation

The MCP package is available as:

npx @prompt-ot/mcp
Enter fullscreen mode Exit fullscreen mode

You will need a scoped PromptOT API key from your PromptOT dashboard.

Claude Desktop

Add this to your Claude Desktop MCP config:

{
  "mcpServers": {
    "promptot": {
      "command": "npx",
      "args": ["-y", "@prompt-ot/mcp"],
      "env": {
        "PROMPTOT_API_KEY": "pot_...",
        "PROMPTOT_MCP_CLIENT": "claude-desktop"
      }
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

PromptOT also provides a desktop extension bundle for Claude Desktop:

https://www.promptot.com/downloads/promptot.mcpb
Enter fullscreen mode Exit fullscreen mode

Cursor

Add this to your Cursor MCP config:

{
  "mcpServers": {
    "promptot": {
      "command": "npx",
      "args": ["-y", "@prompt-ot/mcp"],
      "env": {
        "PROMPTOT_API_KEY": "pot_...",
        "PROMPTOT_MCP_CLIENT": "cursor"
      }
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Codex CLI

Add this to your Codex config:

[mcp_servers.promptot]
command = "npx"
args = ["-y", "@prompt-ot/mcp"]
env = { PROMPTOT_API_KEY = "pot_...", PROMPTOT_MCP_CLIENT = "codex-cli" }
Enter fullscreen mode Exit fullscreen mode

Hosted MCP

PromptOT also has a hosted MCP endpoint:

https://mcp.promptot.com/mcp
Enter fullscreen mode Exit fullscreen mode

This can be used by clients that support hosted MCP connections with OAuth.

Example workflow

Here is a realistic workflow.

You are building an AI support agent. The current system prompt is hardcoded in your app. Every time you want to update the refund policy, escalation rules, or tone, you need to change code, open a pull request, wait for CI, and deploy.

With PromptOT, you can move that system prompt into a managed prompt.

You split it into blocks:

Role
Context
Instructions
Refund policy
Escalation rules
Output format
Guardrails
Enter fullscreen mode Exit fullscreen mode

Your app fetches the published version through the PromptOT API.

Then, with the MCP server connected, you can ask your AI tool to help manage changes:

Open the support-agent prompt and create a draft version with a stricter escalation rule for billing-related complaints.
Enter fullscreen mode Exit fullscreen mode

Then:

Show me the diff between the published version and this draft.
Enter fullscreen mode Exit fullscreen mode

Then:

Create a test case for an angry customer asking for a refund outside the refund window.
Enter fullscreen mode Exit fullscreen mode

Then:

Publish the draft.
Enter fullscreen mode Exit fullscreen mode

This keeps prompt work closer to the tools where developers and AI engineers already think through changes.

Why this matters

Prompt management gets messy because prompts sit between product, engineering, support, and evaluation.

They are not exactly code, but they affect production behavior like code.

A few things become important quickly:

  • Who changed this prompt?
  • What changed between versions?
  • Which version is live?
  • Can we roll back?
  • Can we test this prompt before shipping it?
  • Can we update prompts without redeploying the app?
  • Can AI tools help maintain prompts safely?

PromptOT is designed around those questions.

The MCP server adds another layer: instead of only clicking through a dashboard, you can let your AI development tools interact with the prompt system directly.

Safety model

PromptOT uses scoped API keys for MCP access.

That matters because an MCP server can expose powerful actions. PromptOT separates tool capabilities so clients can understand whether a tool is read-only, destructive, or idempotent.

The goal is to make prompt operations useful without turning every assistant action into an unsafe production change.

Links

Final thought

LLM apps are moving from simple prompt strings to real prompt infrastructure.

Once prompts need versions, variables, publishing, rollback, evaluations, and team workflows, they deserve their own operational layer.

PromptOT MCP is one step toward making prompt management feel native inside the AI tools developers already use.

Top comments (0)