How to integrate Contentful MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Contentful logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Contentful to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Contentful agent that can list all contentful spaces i manage, get details for the 'marketing' space, update the name of your blog space through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Contentful account through Composio's Contentful MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Contentful with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Contentful integration
  • Using Composio's Tool Router to dynamically load and access Contentful tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

What is the Contentful MCP server, and what's possible with it?

The Contentful MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Contentful account. It provides structured and secure access to your Contentful spaces, so your agent can perform actions like listing spaces, retrieving space details, and updating space information on your behalf.

  • List all available spaces: Quickly fetch a comprehensive list of all Contentful spaces you have access to, making it easier to choose where to manage or publish content.
  • Retrieve detailed space information: Ask your agent to pull up full details about any specific Contentful space, including metadata and configuration—great for audits or content planning.
  • Update space names safely: Let your agent rename a space by handling version checks and updates for you, ensuring your workspace stays organized and accurately labeled.
  • Streamline space management: Automate repetitive space-related tasks, like checking which spaces are available or updating their names, so you can focus on content creation.

Supported Tools & Triggers

Tools
Activate Content TypeActivates (publishes) a content type in Contentful.
Archive AssetTool to archive an asset in Contentful.
Archive EntryTool to archive an entry in Contentful.
Archive ReleaseTool to archive a release in Contentful.
Create App Signing KeyTool to generate an app signing key for a Contentful app definition.
Create Content TypeTool to create a new content type in a Contentful environment.
Create Entry TaskTool to create a task on a Contentful entry.
Create EnvironmentTool to create a new environment within a Contentful space.
Create App Access GrantCreates an access grant for an app definition to allow organizations to install the app.
Create Organizations App DefinitionsTool to create a new app definition in a Contentful organization.
Create App Definition ActionTool to create an action for a Contentful app definition.
Create Organization InvitationCreate an invitation to an organization in Contentful (alpha feature).
Create Organizations Security ContactsCreates a security contact for a specific organization.
Create Organizations Taxonomy ConceptsTool to create a new taxonomy concept in a Contentful organization.
Create Organizations Taxonomy Concept SchemesTool to create a new taxonomy concept scheme in an organization.
Create ReleaseTool to create a new release in Contentful.
Create Delivery API KeyTool to create a new Delivery API key for a Contentful space.
Create AssetTool to create a new asset in a Contentful space environment.
Create EntryTool to create a new entry in a Contentful space environment.
Create Entry CommentTool to create a comment on an entry in Contentful.
Create ExtensionTool to create a new UI extension within a Contentful space and environment.
Create Scheduled ActionTool to create a scheduled action for publishing or unpublishing entries/assets in Contentful.
Delete AssetDeletes an asset by ID from a Contentful environment.
Delete Content TypeDeletes a content type by ID from a Contentful environment.
Delete EntryDeletes an entry by ID from a Contentful environment.
Delete EnvironmentDeletes an environment by ID from a Contentful space.
Delete ExtensionDeletes an extension by ID from a Contentful environment.
Delete App Event SubscriptionDeletes an app event subscription from a Contentful organization.
Delete App Definition DetailsTool to delete app definition details for an organization in Contentful.
Delete App KeyTool to delete an app key from an app definition in a Contentful organization.
Delete App Definition Signing SecretTool to remove the current app signing secret from an app definition.
Delete Organization Security ContactDeletes a security contact from a Contentful organization.
Delete ReleaseDeletes a release by ID from a Contentful environment.
Delete Scheduled ActionCancels a scheduled action by ID in Contentful.
Delete Space MembershipDeletes a space membership by ID from a Contentful space.
Delete Delivery API KeyTool to delete a single Delivery API key from a Contentful space.
Delete Spaces UploadDeletes an upload by ID from a Contentful space.
Delete TagDeletes a tag by ID from a Contentful environment.
Get App BundleRetrieves details of a specific app bundle by its ID.
Get App DefinitionTool to retrieve details of a specific app definition by its ID.
Get AssetTool to retrieve a single asset from a Contentful environment by its ID.
Get Content TypesRetrieves all content types in a Contentful environment.
Get Content Type SnapshotTool to retrieve a snapshot of a content type by snapshot ID.
Get Content Type SnapshotsTool to get all snapshots of a content type in Contentful.
Get Editor InterfaceTool to retrieve the editor interface configuration for a content type.
Get Entry CommentTool to retrieve a specific comment from an entry in Contentful.
Get Entry ReferencesTool to retrieve references to a specific entry in Contentful.
Get Entry SnapshotsTool to get all snapshots of an entry in Contentful.
Get EnvironmentTool to retrieve details of a specific environment by its ID within a space.
Get OrganizationRetrieves details of a specific organization by its ID.
Get Organization Access GrantRetrieves the access grant status for a specific organization.
Get OrganizationsTool to get all organizations an account has access to in Contentful.
Get Organizations AI ProvidersRetrieves all AI providers configured for an organization in Contentful.
Get Organization App Actions CategoriesRetrieves app action categories for a Contentful organization.
Get App Event SubscriptionTool to retrieve details of an app event subscription by organization and app definition ID.
Get Organizations App DefinitionsRetrieves all app definitions for a specific organization.
Get Organizations App Definitions Access GrantsGet all app access grants for a specific app definition within an organization.
Get App Definition ActionsTool to get all actions of an app definition within an organization.
Get App Action DetailsTool to read a specific app action from an app definition within an organization.
Get App Definition App BundlesTool to get all app bundles for a specific app definition within an organization.
Get App Definition FunctionsTool to get all functions of an app definition within an organization.
Get App Definition KeysTool to retrieve all app keys for a specific app definition in a Contentful organization.
Get App Definition Signing SecretTool to retrieve the current app signing secret for an app definition.
Get Organization EnablementsRetrieves feature enablements for a specific organization in Contentful.
Get Organization InvitationRetrieves a single invitation for an organization (alpha).
Get Organization Periodic UsagesTool to get organization periodic usage statistics.
Get Organization RolesRetrieves all space roles in an organization.
Get Organization Security ContactsRetrieves security contacts for a specific organization that an admin or owner has access to.
Get Organizations Space EnablementsRetrieves all space enablements for a specific organization.
Get Organizations Space Periodic UsagesTool to retrieve space periodic usage data for an organization.
Get Organizations Taxonomy ConceptsRetrieves all taxonomy concepts for an organization in Contentful.
Get Taxonomy Concept AncestorsRetrieves the list of ancestor concepts for a specific taxonomy concept.
Get Organizations Taxonomy Concept SchemesTool to retrieve all taxonomy concept schemes from an organization.
Get Taxonomy Concept SchemeTool to retrieve a specific taxonomy concept scheme from an organization.
Get Organizations Taxonomy Concept Schemes TotalRetrieves the total count of taxonomy concept schemes for a specific organization.
Get Organizations Taxonomy Concepts TotalRetrieves the total count of taxonomy concepts for a specific organization.
Get ReleaseTool to get a single release by ID from Contentful.
Get spaceRetrieves metadata of a specific space by its ID.
Get Space MembershipsTool to get all space memberships in a Contentful space.
Get Delivery API KeysTool to retrieve all Delivery API keys for a specific Contentful space.
Get Space EnvironmentsRetrieves all environments of a space in Contentful.
List App InstallationsLists all app installations in a specific Contentful environment.
Get All AssetsRetrieves all assets from a specific environment in a Contentful space.
Get Space Environment LocalesTool to retrieve all locales of a space environment in Contentful.
Get App Installation FunctionsTool to get all functions for an app installation in a Contentful environment.
Get Authenticated UserTool to retrieve information about the currently authenticated user.
List EntriesTool to retrieve all entries from a Contentful space environment.
List spacesLists all spaces that the authenticated user has access to in Contentful.
Get All Space RolesTool to retrieve all roles from a Contentful space.
Publish EntryTool to publish an entry in Contentful, making it available via the Content Delivery API.
Query Asset CollectionTool to retrieve multiple assets with pagination and filtering via GraphQL API.
Query GraphQL Content Type CollectionTool to query a collection of entries for a specific content type using GraphQL.
Update App DefinitionTool to update an app definition by ID in a Contentful organization.
Update Editor InterfaceTool to update the editor interface configuration for a content type.
Update EntryTool to create or update an entry in a Contentful space environment.
Update App Event SubscriptionTool to update or create an app event subscription in a Contentful organization.
Update App Definition ActionTool to update an action for a Contentful app definition.
Update App Definition DetailsTool to create or update app definition details for an organization in Contentful.
Update App Definition Signing SecretTool to create or overwrite the app signing secret for an app definition.
Update Organization EnablementsUpdates feature enablements for a specific organization in Contentful.
Update Organization Security ContactUpdates an organization security contact that an admin or owner has access to.
Update Organizations Taxonomy ConceptsTool to create or update a taxonomy concept with a user-defined ID in a Contentful organization.
Update Organizations Taxonomy Concept SchemesTool to create or update a taxonomy concept scheme with a user-defined ID in an organization.
Update spaceUpdates the name of a specific space.
Update TagCreates or updates a tag in a Contentful environment.
Validate Bulk ActionTool to validate a bulk action before executing it.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["contentful"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Contentful tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Contentful-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Contentful tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to contentful, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Contentful tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Contentful and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["contentful"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to contentful, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Contentful agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Contentful MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Contentful MCP?

With a standalone Contentful MCP server, the agents and LLMs can only access a fixed set of Contentful tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Contentful and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Vercel AI SDK v6?

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Contentful tools.

Can I manage the permissions and scopes for Contentful while using Tool Router?

Yes, absolutely. You can configure which Contentful scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Contentful data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.