Prompt MCP Server

Decorator-based integration testing for LLM prompts

Local serverstdioPython

What is the Prompt MCP server?

Most AI and media services work still happens through a UI a human drives. Prompt MCP server moves it into the conversation instead. Decorator-based integration testing for LLM prompts.

The short version

Decorator-based integration testing for LLM prompts. Wrap a test function with @prompt_run, and it sends your prompt to a real model, then hands you the response to assert on — with an LLM judge for the assertions that plain string checks can't express.

The tools it exposes

The server publishes 6 tools. What each one is for:

  • ask_all — many independent checks where cost matters and slight cross-contamination between questions is acceptable
  • ask_parallel — questions that must be fully isolated, without the latency of sequential ask calls
  • ask — a single question, or when you need to branch on the result before asking the next
  • Method — API calls
  • Methods — The Methods tool exposed by this server
  • Fields — The Fields tool exposed by this server

What it needs from you

Configuration is passed through the environment: ANTHROPIC_API_KEY, GOOGLE_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

prompt-tester on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Prompt's toolset — ask_all, ask_parallel, ask and 3 more — is a fair guide to whether it matches your workflow.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
ask_allmany independent checks where cost matters and slight cross-contamination between questions is acceptable.
ask_parallelquestions that must be fully isolated, without the latency of sequential ask calls.
aska single question, or when you need to branch on the result before asking the next.
MethodAPI calls
MethodsThe Methods tool exposed by this server.
FieldsThe Fields tool exposed by this server.

How to install the Prompt MCP server

{
  "mcpServers": {
    "prompt-tester": {
      "command": "uvx",
      "args": ["prompt-tester"],
      "env": {
        "ANTHROPIC_API_KEY": "your-value",
        "GOOGLE_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
ANTHROPIC_API_KEYCredential the server authenticates with.Yes
GOOGLE_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Prompt to ask all.
  • Use Prompt to ask parallel.
  • Use Prompt to ask.

Frequently asked questions

It connects Prompt to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (ask_all, ask_parallel, ask, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Prompt directly.