How to integrate Confluence MCP with Vercel AI SDK

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

Introduction

This guide walks you through connecting Confluence to Vercel AI SDK using the Composio tool router. By the end, you'll have a working Confluence agent that can create a project documentation page in marketing space, add 'urgent' label to q3 planning page, publish team meeting summary as a blog post, create a private space for product roadmap drafts through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Confluence account through Composio's Confluence 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 Confluence integration
  • Using Composio's Tool Router to dynamically load and access Confluence 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 Confluence MCP server, and what's possible with it?

The Confluence MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Confluence account. It provides structured and secure access to your Confluence spaces, pages, and content, so your agent can perform actions like creating pages, publishing blog posts, organizing spaces, and managing metadata on your behalf.

  • Automated page and space creation: Instantly create new Confluence pages or entire spaces, empowering your agent to generate project documentation, wikis, or knowledge bases as needed.
  • Effortless blog post publishing: Let your agent draft and publish new blog posts within specified Confluence spaces to keep your team up-to-date and share knowledge seamlessly.
  • Content labeling and metadata management: Have your agent add labels and custom properties to pages, blog posts, or spaces, making it easy to organize, tag, and categorize information for better discoverability.
  • Private space setup and management: Direct your agent to create private, isolated workspaces for sensitive projects or teams, ensuring only authorized collaborators have access.
  • Custom content property automation: Empower your agent to attach or update custom metadata on pages, blog posts, spaces, or whiteboards, streamlining your internal documentation workflows.

Supported Tools & Triggers

Tools
Add Content LabelTool to add labels to a piece of content.
Get Space by IDTool to retrieve a confluence space by its id.
Create BlogpostTool to create a new confluence blog post.
Create Blogpost PropertyTool to create a property on a specified blog post.
Create Whiteboard PropertyTool to create a new content property on a whiteboard.
Create PageTool to create a new confluence page in a specified space.
Create Page PropertyTool to create a property on a confluence page.
Create Private SpaceTool to create a private confluence space.
Create SpaceTool to create a new confluence space.
Create Space PropertyTool to create a new property on a confluence space.
Create WhiteboardTool to create a new confluence whiteboard.
Delete Blogpost PropertyTool to delete a blog post property.
Delete Page Content PropertyTool to delete a content property from a page by property id.
Delete Whiteboard Content PropertyTool to delete a content property from a whiteboard by property id.
Delete PageTool to delete a confluence page.
Delete SpaceTool to delete a confluence space by its key.
Delete Space PropertyTool to delete a space property.
Get Attachment LabelsTool to list labels on an attachment.
Get AttachmentsTool to retrieve attachments of a confluence page.
Get Audit LogsTool to retrieve confluence audit records.
Get Blogpost by IDTool to retrieve a specific confluence blog post by its id.
Get Blogpost LabelsTool to retrieve labels of a specific confluence blog post by id.
Get Blogpost Like CountTool to get like count for a confluence blog post.
Get Blogpost OperationsTool to retrieve permitted operations for a confluence blog post.
Get BlogpostsTool to retrieve a list of blog posts.
Get Blog PostsTool to retrieve a list of blog posts.
Get Blog Posts For LabelTool to list all blog posts under a specific label.
Get Blogpost Version DetailsTool to retrieve details for a specific version of a blog post.
Get Blogpost VersionsTool to retrieve all versions of a specific blog post.
Get Child PagesTool to list all direct child pages of a given confluence page.
Get Blog Post Content PropertiesTool to retrieve all content properties on a blog post.
Get Page Content PropertiesTool to retrieve all content properties on a page.
Get Content RestrictionsTool to retrieve restrictions on a confluence content item.
Get Current UserTool to get information about the currently authenticated user.
Get Inline Comments for Blog PostTool to retrieve inline comments for a confluence blog post.
Get LabelsTool to retrieve all labels in a confluence site.
Get Page LabelsTool to retrieve labels of a specific confluence page by id.
Get Labels for SpaceTool to list labels on a space.
Get Labels for Space ContentTool to list labels on all content in a space.
Get Page AncestorsTool to retrieve all ancestors for a given confluence page by its id.
Get Page by IDTool to retrieve a confluence page by its id.
Get Page Like CountTool to get like count for a confluence page.
Get PagesTool to retrieve a list of pages.
Get Page VersionsTool to retrieve all versions of a specific confluence page.
Get Space by IDTool to retrieve a confluence space by its id.
Get Space ContentsTool to retrieve content in a confluence space.
Get Space PropertiesTool to get properties of a confluence space.
Get SpacesTool to retrieve a list of confluence spaces.
Get Anonymous UserTool to retrieve information about the anonymous user.
Search ContentSearches for content by filtering pages from the confluence v2 api with intelligent ranking.
Search UsersSearches for users using user-specific queries from the confluence query language (cql).
Update BlogpostTool to update a confluence blog post's title or content.
Update Blogpost PropertyTool to update a property of a specified blog post.
Update Page Content PropertyTool to update a content property on a confluence page.
Update Whiteboard Content PropertyTool to update a content property on a whiteboard.
Update PageTool to update an existing confluence page.
Update Space PropertyTool to update a space property.

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: ["confluence"],
  });

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

  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 confluence, 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 Confluence 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 Confluence MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Confluence MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Confluence MCP with Claude Agent SDK

Google ADK

Google ADK

Use Confluence MCP with Google ADK

LangChain

LangChain

Use Confluence MCP with LangChain

Mastra AI

Mastra AI

Use Confluence MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Confluence MCP with LlamaIndex

CrewAI

CrewAI

Use Confluence MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Confluence 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 Confluence 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