MCP Catalogs
← Home

gen-ai-starter

by jbsoftware-io·★ 3·Score 36

Generative AI starter with MCP integration for converting REST APIs to standardized tools.

ai-llmdeveloper-toolsother
1
Forks
5
Open issues
this month
Last commit
2d ago
Indexed

Overview

This is a comprehensive generative AI starter kit that incorporates several open source tools and models, including Ollama, Open WebUI, LangChain, Streamlit, Chroma, and PGVector. It containerizes the application using Docker and Docker Compose. The project specifically supports Model Context Protocol (MCP) servers, enabling standardized tool loading from OpenAPI specifications. It includes a complete MCP server generated from the PokéAPI OpenAPI specification, demonstrating how to convert REST APIs to standardized MCP tools and deploy them independently.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Building custom agentic LLM applications with RAG capabilities
you:Converting existing REST API services into MCP tools for AI agents
you:Developing and testing LLM applications with Streamlit web interface
you:What is the purpose of the MCP server in this project?
you:How can I create an MCP server for my own API?

When to choose this

Choose this as a learning resource for understanding how to convert REST APIs to MCP tools or when you need a working example of MCP server implementation.

When NOT to choose this

Not suitable for production use as this is primarily a starter project with a single API example (PokéAPI) rather than a comprehensive MCP server framework.

Tools this server exposes

8 tools extracted from the README
  • pokemon_mcp

    Query PokéAPI to get information about Pokémon

  • ollama_list_models

    List available Ollama models

  • create_github_issue

    Create a new GitHub issue

  • search_brave

    Search the web using Brave Search API

  • explain_code

    Explain a specific file or code pattern

  • guide_learning

    Get structured guidance through learning topics

  • create_learning_path

    Create personalized learning progressions

  • implement_feature

    Get help implementing new features

Note: Tools were inferred from documentation examples and usage patterns rather than explicit MCP tool listings. The actual MCP tools are likely generated from OpenAPI specifications as mentioned in the README.

Comparable tools

openapi-mcp-generatormcp-server-templateapi-to-mcp

Installation

Installation

  1. Prerequisites:

- Docker Engine (>= 12 GB memory or >= 8 GB with Ollama executable) - Optional: Brave Search API key for web search example

  1. Quick start with CPU:

``bash docker compose --profile=cpu up -d ``

  1. Access the applications:

- Streamlit App: http://localhost:8501/ - Open WebUI: http://localhost:3000/

  1. For MCP server generation:

``bash npm install -g openapi-mcp-generator openapi-mcp-generator --input path/to/openapi.json --output my-mcp-server --transport streamable-http ``

FAQ

What is the purpose of the MCP server in this project?
The MCP server enables standardized tool loading from OpenAPI specifications, allowing developers to convert REST APIs into MCP tools that can be used by AI agents.
How can I create an MCP server for my own API?
You can use the openapi-mcp-generator CLI tool. Install it with 'npm install -g openapi-mcp-generator', then generate your server with 'openapi-mcp-generator --input your-openapi.json --output your-mcp-server'.

Compare gen-ai-starter with

gen-ai-starter vs ultimate_mcp_servergen-ai-starter vs mcp-server-chartgen-ai-starter vs everythinggen-ai-starter vs filesystemgen-ai-starter vs time
GitHub →

Last updated · Auto-generated from public README + GitHub signals.