V2 AI

You run a lightweight MCP server that scrapes blog content from V2.ai Insights, extracts key fields, and generates AI-powered summaries using GPT-4. It also exposes tools that integrate with Claude Desktop for convenient access to the content and search capabilities.

How to use

You connect to the MCP server from your MCP client to access the available tools. Use the following tools to fetch, search, and summarize blog content: get_latest_posts, get_contentful_posts, search_blogs, summarize_post, and get_post_content. The server automatically selects the best available source (Contentful CMS or V2.ai web scraping) to return posts and content.

How to install

Prerequisites you need before installing this MCP server are Python 3.12 or higher, the uv package manager, an OpenAI API key, and Contentful CMS credentials if you want enhanced Contentful integration.

1. Clone and navigate to the project directory.

dcd v2-ai-mcp

2. Install dependencies using the uv package manager.

uv add fastmcp beautifulsoup4 requests openai

3. Create and configure environment variables. Copy the example and fill in your credentials.

cp .env.example .env

Edit the .env file to include your API keys and Contentful credentials.

# Required
OPENAI_API_KEY=your-openai-api-key-here

# Optional (for Contentful integration)
CONTENTFUL_SPACE_ID=your-contentful-space-id
CONTENTFUL_ACCESS_TOKEN=your-contentful-access-token
CONTENTFUL_CONTENT_TYPE=pageBlogPost

4. Start the MCP server.

uv run python -m src.v2_ai_mcp.main

Additional notes

Claude Desktop integration is supported. You can configure the MCP in Claude Desktop to connect to this server and access all tools directly from the Claude interface.

Example Claude Desktop MCP configuration (stdio) shown below demonstrates how to launch the server and pass environment variables.

{
  "mcpServers": {
    "v2_insights": {
      "command": "/path/to/uv",
      "args": ["run", "--directory", "/path/to/your/v2-ai-mcp", "python", "-m", "src.v2_ai_mcp.main"],
      "env": {
        "OPENAI_API_KEY": "your-api-key-here",
        "CONTENTFUL_SPACE_ID": "your-contentful-space-id",
        "CONTENTFUL_ACCESS_TOKEN": "your-contentful-access-token",
        "CONTENTFUL_CONTENT_TYPE": "pageBlogPost"
      }
    }
  }
}

Testing and troubleshooting

You can test individual components and the overall MCP startup to ensure everything runs smoothly. If you encounter authentication errors, verify you set your OPENAI_API_KEY correctly. If content fetching fails, check Contentful credentials and connection settings. You can also run unit tests for scraper and summarizer modules when needed.

Available tools

get_latest_posts

Retrieves blog posts with metadata using Contentful data when available, with a V2.ai scrape fallback if Contentful data is missing.

get_contentful_posts

Fetch posts directly from the Contentful CMS using the configured space and access token.

search_blogs

Performs a full-text search across all blog content using the integrated search capabilities.

summarize_post

Returns an AI-generated summary for a specific post, using OpenAI GPT-4.

get_post_content

Returns the full content of a specific post by index or identifier.