Contentful Delivery MCP server for AI agents

This MCP server provides seamless access to Contentful's Delivery API through AI assistants, allowing you to query and retrieve content entries, assets, and content types using natural language.

Installation

You can install the Contentful Delivery MCP server in your project using npm:

npm install @mshaaban0/contentful-delivery-mcp-server

Or install it globally:

npm install -g @mshaaban0/contentful-delivery-mcp-server

Configuration

Set up your Contentful credentials using environment variables:

export CONTENTFUL_SPACE_ID="your_space_id"
export CONTENTFUL_ACCESS_TOKEN="your_access_token"
# Optional: Restrict content to specific content types
export CONTENTFUL_CONTENT_TYPE_IDS="blogPost,article,product"

Available Tools

The server provides several tools to interact with your Contentful content:

query_entries - Search across all content using natural language
get_entry - Fetch a specific entry by ID
get_entries - List entries with filtering options
get_assets - Browse all assets in your space
get_asset - Get detailed information about a specific asset by ID
get_content_type - View schema details for a content type
get_content_types - List all available content types

Integration with Mastra AI

Here's how to integrate this MCP server with Mastra AI:

import { MastraMCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";

// Initialize the MCP client
const contentfulClient = new MastraMCPClient({
  name: "contentful-delivery",
  server: {
    command: "npx",
    args: ["-y", "@mshaaban0/contentful-delivery-mcp-server@latest"],
    env: {
      CONTENTFUL_ACCESS_TOKEN: "your_access_token",
      CONTENTFUL_SPACE_ID: "your_space_id",
      // Optional: Restrict content to specific content types
      CONTENTFUL_CONTENT_TYPE_IDS: "blogPost,article,product"
    }
  }
});

// Create an AI agent with access to Contentful
const assistant = new Agent({
  name: "Content Assistant",
  instructions: `
    You are a helpful assistant with access to our content database.
    Use the available tools to find and provide accurate information.
  `,
  model: "gpt-4",
});

// Connect and register tools
await contentfulClient.connect();
const tools = await contentfulClient.tools();
assistant.__setTools(tools);

// Example usage
const response = await assistant.chat("Find articles about machine learning");

Using the Debugging Tools

The MCP server includes a web interface for debugging:

npm run inspector

After running this command, visit the provided URL in your browser to access the debugging tools.

Additional Resources

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "contentful-delivery" '{"command":"npx","args":["-y","@mshaaban0/contentful-delivery-mcp-server@latest"],"env":{"CONTENTFUL_ACCESS_TOKEN":"your_access_token","CONTENTFUL_SPACE_ID":"your_space_id","CONTENTFUL_CONTENT_TYPE_IDS":"blogPost,article,product"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "contentful-delivery": {
            "command": "npx",
            "args": [
                "-y",
                "@mshaaban0/contentful-delivery-mcp-server@latest"
            ],
            "env": {
                "CONTENTFUL_ACCESS_TOKEN": "your_access_token",
                "CONTENTFUL_SPACE_ID": "your_space_id",
                "CONTENTFUL_CONTENT_TYPE_IDS": "blogPost,article,product"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "contentful-delivery": {
            "command": "npx",
            "args": [
                "-y",
                "@mshaaban0/contentful-delivery-mcp-server@latest"
            ],
            "env": {
                "CONTENTFUL_ACCESS_TOKEN": "your_access_token",
                "CONTENTFUL_SPACE_ID": "your_space_id",
                "CONTENTFUL_CONTENT_TYPE_IDS": "blogPost,article,product"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect