How to integrate Notion MCP with Vercel AI SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Notion Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting Notion to Vercel AI SDK using the Composio tool router. By the end, you'll have a working Notion agent that can add meeting notes to project wiki page, create a new task database for q3, archive completed sprint summary pages, duplicate onboarding checklist for new hire through natural language commands.

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

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

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Notion integration
  • Using Composio's Tool Router to dynamically load and access Notion 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
  • Step Counting: Control multi-step tool execution
  • OpenAI Provider: Native integration with OpenAI models

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

The Notion MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Notion account. It provides structured and secure access to your notes, docs, wikis, and tasks, so your agent can perform actions like creating pages, managing databases, adding content, commenting, and organizing your Notion workspace for you.

  • Bulk content creation and formatting: Let your agent efficiently add and format multiple blocks of text, lists, or markdown content to Notion pages in one go.
  • Automated page and database management: Have your agent create new pages, duplicate existing ones, or set up entire databases with custom properties—no manual setup required.
  • Smart commenting and collaboration: Enable your agent to add comments to pages or discussion threads, making real-time collaboration smoother.
  • Workspace organization and cleanup: Ask your agent to archive, delete, or restore pages and blocks, keeping your workspace tidy and up to date.
  • Deep block and structure retrieval: Direct your agent to fetch metadata, list child blocks, or dig into nested content for analysis, reporting, or workflow automation.

Supported Tools & Triggers

Tools
Triggers
Add multiple content blocks (bulk, user-friendly)Efficiently adds multiple standard content blocks to a notion page in a single api call with automatic markdown parsing.
Append complex blocks (advanced, full control)Appends complex blocks with full notion block structure to a parent block or page.
Archive Notion PageArchives (moves to trash) or unarchives (restores from trash) a specified notion page.
Create commentAdds a comment to a notion page (via `parent page id`) or to an existing discussion thread (via `discussion id`); cannot create new discussion threads on specific blocks (inline comments).
Create Notion DatabaseCreates a new notion database as a subpage under a specified parent page with a defined properties schema; use this action exclusively for creating new databases.
Create Notion pageCreates a new empty page in a notion workspace.
Delete a blockArchives a notion block, page, or database using its id, which sets its 'archived' property to true (like moving to "trash" in the ui) and allows it to be restored later.
Duplicate pageDuplicates a notion page, including all its content, properties, and nested blocks, under a specified parent page or workspace.
Fetch Notion Block ChildrenRetrieves a paginated list of direct, first-level child block objects along with contents for a given parent notion block or page id; use block ids from the response for subsequent calls to access deeply nested content.
Fetch Notion block metadataFetches metadata for a notion block (or page, as pages are blocks) using its valid uuid; if the block has children, use fetch block contents to fetch their contents.
Fetch commentsFetches unresolved comments for a specified notion block or page id.
Fetch Notion DataFetches notion items (pages and/or databases) from the notion workspace, use this to get minimal data about the items in the workspace with a query or list all items in the workspace with minimal data
Fetch DatabaseFetches a notion database's structural metadata (properties, title, etc.
Fetch database rowRetrieves a notion database row's properties and metadata; use fetch block contents for page content blocks.
Get About MeRetrieves the user object for the bot associated with the current notion integration token, typically to obtain the bot's user id for other api operations.
Get about userRetrieves detailed information about a specific notion user, such as their name, avatar, and email, based on their unique user id.
Get page propertyCall this to get a specific property from a notion page when you have a valid `page id` and `property id`; handles pagination for properties returning multiple items.
Insert row databaseCreates a new page (row) in a specified notion database.
List usersRetrieves a paginated list of users (excluding guests) from the notion workspace; the number of users returned per page may be less than the requested `page size`.
Query databaseQueries a notion database for pages (rows), where rows are pages and columns are properties; ensure sort property names correspond to existing database properties.
Retrieve CommentTool to retrieve a specific comment by its id.
Retrieve Database PropertyTool to retrieve a specific property object of a notion database.
Search Notion pageSearches notion pages and databases by title; an empty query lists all accessible items, useful for discovering ids or as a fallback when a specific query yields no results.
Update blockUpdates an existing notion block's textual content or type-specific properties (e.
Update PageTool to update the properties, icon, cover, or archive status of a page.
Update row databaseUpdates or archives an existing notion database row (page) using its `row id`, allowing modification of its icon, cover, and/or properties; ensure the target page is accessible and property details (names/ids and values) align with the database schema and specified formats.
Update database schemaUpdates an existing notion database's title, description, and/or properties; at least one of these attributes must be provided to effect a change.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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 { experimental_createMCPClient as 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: ["notion"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Notion 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 Notion-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 Notion 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 notion, 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 Notion 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 Notion 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 { experimental_createMCPClient as 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: ["notion"],
  });

  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 notion, 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 Notion 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 Notion MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Notion MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Notion MCP with Claude Agent SDK

Google ADK

Google ADK

Use Notion MCP with Google ADK

LangChain

LangChain

Use Notion MCP with LangChain

Mastra AI

Mastra AI

Use Notion MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Notion MCP with LlamaIndex

CrewAI

CrewAI

Use Notion MCP with CrewAI

FAQ

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

With a standalone Notion MCP server, the agents and LLMs can only access a fixed set of Notion tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Notion 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?

Yes, you can. Vercel AI SDK 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 Notion tools.

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

Yes, absolutely. You can configure which Notion 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 Notion data and credentials are handled as safely as possible.

Used by agents from

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

Book a call↗Get started for free