How to integrate Hashnode MCP with Vercel AI SDK v6

This guide walks you through connecting Hashnode to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Hashnode agent that can list your most recent hashnode articles, check if 'devjournal.com' domain is available, fetch popular tags for trending topics through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Hashnode account through Composio's Hashnode MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Hashnode logoHashnode
Api Key

Hashnode is a blogging platform designed for developers to create, manage, and share technical content. It streamlines publishing and helps grow your dev audience effortlessly.

67 Tools

Introduction

This guide walks you through connecting Hashnode to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Hashnode agent that can list your most recent hashnode articles, check if 'devjournal.com' domain is available, fetch popular tags for trending topics through natural language commands.

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

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

Also integrate Hashnode with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Hashnode integration
  • Using Composio's Tool Router to dynamically load and access Hashnode 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 Hashnode MCP server, and what's possible with it?

The Hashnode MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Hashnode account. It provides structured and secure access to your blog and developer publication data, so your agent can fetch articles, manage publication invites, reply to comments, and explore tags or user details on your behalf.

  • Fetch and analyze articles: Let your agent retrieve single articles or lists of posts from your publications, making it easy to summarize, review, or manage your content.
  • Publication invite handling: Effortlessly accept publication invitations or view all your pending invites, streamlining the process of joining new developer teams or publications.
  • Interact with comments and replies: Have your agent add replies to existing comments, enabling automated engagement and conversation management on your posts.
  • Tag discovery and trend tracking: Easily fetch popular tags so your agent can suggest relevant topics, optimize your writing focus, or help you follow industry trends.
  • User and publication insights: Retrieve detailed profile information for any user or publication, giving your agent the context needed for personalized recommendations and content actions.

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

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

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.
3

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
4

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
5

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
6

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: ["hashnode"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Hashnode 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 Hashnode-related tools through the MCP protocol
7

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 Hashnode tools that the agent can use
8

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 hashnode, 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
9

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 Hashnode 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 Hashnode 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: ["hashnode"],
  });

  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 hashnode, 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 Hashnode 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.
TOOLS

Supported Tools

Every Hashnode action and event your agent gets out of the box.

Hashnode Accept Publication Invite

Tool to accept a publication invitation.

Hashnode Add Comment

Add a comment to a Hashnode post.

Hashnode Add Content Block

Tool to add a content block to a Hashnode documentation project.

Hashnode Add Custom MDX Component

Tool to add a custom MDX component to a Hashnode documentation project.

Hashnode: Add Documentation Project Custom Domain

Tool to add a custom domain to a Hashnode documentation project.

Hashnode Add Reply

Tool to add a reply to an existing comment.

Hashnode: Check Custom Domain Availability

Tool to check if a custom domain is available for your Hashnode publication.

Hashnode: Check Subdomain Availability

Tool to check if a subdomain is available for a Hashnode publication.

Create Documentation API Reference

Tool to create a documentation API reference from an OpenAPI specification URL in a Hashnode project.

Create Documentation Link

Tool to create a link within a Hashnode documentation guide.

Hashnode: Create Documentation Project

Tool to create a new documentation project on Hashnode.

Hashnode Create Documentation Section

Tool to create a new documentation section in a Hashnode documentation guide.

Create Hashnode Documentation Guide

Tool to create a new documentation guide in a Hashnode documentation project.

Hashnode Delete Content Block

Tool to delete a content block from a Hashnode documentation project.

Hashnode Delete Custom MDX Component

Tool to delete a custom MDX component from a Hashnode documentation project.

Disable Documentation Project AI Search

Tool to disable AI search for a documentation project on Hashnode.

Hashnode: Fetch Invitations

Fetch pending publication invitations for a Hashnode publication.

Hashnode: Fetch Popular Tags

Tool to fetch a paginated list of popular tags.

Fetch Publication Posts

Tool to fetch a paginated list of posts from a publication.

Fetch Series Posts

Tool to fetch posts from a series within a publication.

Fetch Single Article

Tool to fetch a single article by slug from a publication.

Fetch Stories Feed

Fetch a paginated feed of stories from Hashnode.

Hashnode: Fetch User Details

Tool to fetch detailed user profile information by username.

Hashnode: Follow Tags

Follow specified tags to customize your content feed on Hashnode.

Generate Documentation Project Preview Authorization Token

Tool to generate a JWT authorization token for previewing a documentation project.

Get Documentation Project

Tool to fetch details of a Docs by Hashnode project by ID or hostname.

Get Post by ID

Tool to retrieve a published post by ID from Hashnode.

Get Publication by ID or Host

Tool to fetch publication details by ID or hostname.

Hashnode: Get Tag Details

Tool to fetch detailed information about a tag by its slug.

Hashnode Like Comment

Tool to like a comment on Hashnode.

Hashnode Like Post

Tool to like a post on Hashnode.

Hashnode: Like Reply

Tool to like a reply on Hashnode.

Hashnode: List Publications

Tool to list all publications of the authenticated user.

Hashnode: List Top Commenters

Tool to fetch users who have most actively participated in discussions by commenting in the last 7 days.

Hashnode: Map Documentation Project WWW Redirect

Tool to configure WWW redirect for a documentation project's custom domain.

Hashnode: Get Current User

Retrieves profile details of the currently authenticated Hashnode user.

Move Documentation Sidebar Item

Tool to reorder documentation sidebar items within a Hashnode guide.

Publish Documentation API Reference

Tool to publish a documentation API reference in a Hashnode documentation project.

Hashnode Publish Post

Tool to publish a new blog post to a Hashnode publication.

Hashnode Remove Comment

Tool to remove a comment from a Hashnode post.

Hashnode Remove Documentation Guide

Tool to remove a documentation guide from a Hashnode project.

Remove Documentation Project

Tool to remove a documentation project from Hashnode.

Hashnode Remove Documentation Project Custom Domain

Tool to remove a custom domain from a Hashnode documentation project.

Remove Documentation Sidebar Item

Tool to remove a sidebar item from a documentation guide on Hashnode.

Hashnode Remove Post

Tool to remove (delete) a post from Hashnode.

Hashnode Remove Reply

Tool to remove a reply from a comment.

Hashnode Rename Documentation Guide

Tool to rename a documentation guide in a Hashnode project.

Rename Documentation Sidebar Item

Tool to rename a documentation sidebar item within a Hashnode guide.

Hashnode Restore Post

Tool to restore a previously deleted Hashnode post.

Save Documentation Page Draft Content

Tool to save draft content for a documentation page in Hashnode.

Search Posts of Publication

Tool to search and retrieve posts from a specific publication based on a search query.

Subscribe to Newsletter

Tool to subscribe an email address to a Hashnode publication's newsletter.

Hashnode: Toggle Follow User

Tool to toggle follow status for a Hashnode user.

Hashnode: Unfollow Tags

Unfollow specified tags to customize your content feed on Hashnode.

Unsubscribe from Newsletter

Tool to unsubscribe an email address from a Hashnode publication's newsletter.

Hashnode Update Comment

Tool to update an existing comment on a Hashnode post.

Hashnode Update Content Block

Tool to update a content block in a Hashnode documentation project.

Update Documentation Appearance

Tool to update the appearance settings of a Hashnode documentation project.

Update Documentation General Settings

Tool to update general settings of a Hashnode documentation project.

Update Hashnode Documentation Guide

Tool to update an existing documentation guide in a Hashnode project.

Hashnode: Update Documentation Integrations

Tool to update third-party integrations for a Docs by Hashnode project.

Update Documentation Link

Tool to update an existing link within a Hashnode documentation guide.

Hashnode: Update Documentation Project Subdomain

Tool to update the subdomain of a Hashnode documentation project.

Hashnode Update Documentation Section

Tool to update a section in a Hashnode documentation guide.

Hashnode Update Post

Tool to update an existing Hashnode post via the updatePost mutation.

Hashnode Update Reply

Tool to update a reply.

Hashnode Verify Documentation Project Custom Domain

Tool to verify a custom domain for a Hashnode documentation project.

FRAMEWORKS

How to build Hashnode MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Hashnode MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Hashnode MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Hashnode MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Hashnode MCP with Claude Cowork

Codex logo

Codex

Use Hashnode MCP with Codex

OpenClaw logo

OpenClaw

Use Hashnode MCP with OpenClaw

Hermes logo

Hermes

Use Hashnode MCP with Hermes

CLI logo

CLI

Use Hashnode MCP with CLI

Google ADK logo

Google ADK

Use Hashnode MCP with Google ADK

LangChain logo

LangChain

Use Hashnode MCP with LangChain

Mastra AI logo

Mastra AI

Use Hashnode MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Hashnode MCP with LlamaIndex

CrewAI logo

CrewAI

Use Hashnode MCP with CrewAI

FAQ

Frequently asked questions

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

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 Hashnode tools.

Yes, absolutely. You can configure which Hashnode 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.

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 Hashnode data and credentials are handled as safely as possible.

Start with Hashnode.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Hashnode tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies