MCP.so
Sign In

mcp_prompt_mapper

@Sumedh1599

Repository

About mcp_prompt_mapper

Generates optimal Claude/OpenAI-ready prompts to build each part of the MCP server (resources, tools, prompts) from the input generated by `mcp_input_analyzer`.

#open-source#machine-learning#library#ai#prompt-templating

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp_prompt_mapper": {
      "command": "python",
      "args": [
        "setup.py",
        "install"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is mCP Prompt Mapper?

mcp_prompt_mapper is an open‑source library that generates optimal prompts for Claude, Grok, and OpenAI APIs. It takes input from the companion mcp_input_analyzer and transforms it into structured, efficient prompts for building resources, tools, and additional prompts within an MCP server.

How to use mCP Prompt Mapper?

Install via pip (pip install mcp_prompt_mapper) or from source. In code, import PromptMapper, optionally specify output_format='json' or 'yaml', then call generate_prompts(input_data) with a dictionary. Examples for basic, YAML output, and streaming input are provided.

Key features of mCP Prompt Mapper

  • Prompt templating for resources and tools
  • Custom output formats: JSON and YAML
  • Cross‑API compatibility with Claude, Grok, OpenAI
  • Schema‑aware auto‑complete prompts
  • Streaming input parsing for Claude Desktop

Use cases of mCP Prompt Mapper

  • Generate optimised prompts from the mcp_input_analyzer for MCP server components
  • Create schema‑compliant resource and tool templates in JSON or YAML
  • Build prompts that work across multiple LLM APIs (Claude, Grok, OpenAI)
  • Process streaming input directly in Claude Desktop

FAQ from mCP Prompt Mapper

What APIs does mCP Prompt Mapper support?

It supports Claude, Grok, and OpenAI APIs.

What output formats are available?

Prompts can be generated in JSON (default) or YAML format.

How do I install mCP Prompt Mapper?

Use pip install mcp_prompt_mapper or clone the repository and run python setup.py install.

What input format does generate_prompts expect?

It accepts a dictionary of input data, typically from mcp_input_analyzer.

Is mCP Prompt Mapper production‑ready?

The library is in early development; some tests may be failing. Contributions are welcome.

Frequently asked questions

What APIs does mCP Prompt Mapper support?

It supports Claude, Grok, and OpenAI APIs.

What output formats are available?

Prompts can be generated in JSON (default) or YAML format.

How do I install mCP Prompt Mapper?

Use `pip install mcp_prompt_mapper` or clone the repository and run `python setup.py install`.

What input format does `generate_prompts` expect?

It accepts a dictionary of input data, typically from `mcp_input_analyzer`.

Is mCP Prompt Mapper production‑ready?

The library is in early development; some tests may be failing. Contributions are welcome.

Comments

Basic information

Category

AI & Agents

Transports

stdio

Author

Sumedh1599

More AI & Agents MCP servers

Competitor Tracker & Co.

Competitor Tracker & Co.

Competitor Tracker & Co. watches your competitors' websites and tells you what changed. Every week it crawls their pricing, product, messaging and corporate pages, detects the changes that matter, and files a tagged, ran

Perplexity Ask MCP Server

ppl-ai

The official MCP server implementation for the Perplexity API Platform

2.4K

MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages

utensils

MCP-NixOS - Model Context Protocol Server for NixOS resources

739

Sequential Thinking Multi-Agent System (MAS)

FradSer

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

306

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768