How to integrate Ahrefs MCP with Vercel AI SDK

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

Introduction

This guide walks you through connecting Ahrefs to Vercel AI SDK using the Composio tool router. By the end, you'll have a working Ahrefs agent that can get domain rating trend for competitor site, list all broken backlinks for my website, find keyword volume for 'ai tools' in us, show top referring domains for example.com through natural language commands.

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

The Ahrefs MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ahrefs account. It provides structured and secure access to your SEO and marketing data, so your agent can perform actions like analyzing backlinks, researching keywords, auditing domain authority, and uncovering competitive insights on your behalf.

  • Comprehensive backlink analysis: Instantly retrieve detailed backlink profiles, stats, and broken link data for any website to inform your SEO strategy or spot link-building opportunities.
  • Keyword research and trends: Explore keyword overviews, search volumes by country, and discover matching or related terms to optimize content and target the right audience.
  • Domain authority tracking: Fetch up-to-date domain ratings or track historical changes to monitor the SEO health and growth of your own sites or competitors over time.
  • Batch competitor and site analysis: Analyze up to 100 domains or URLs at once to compare SEO metrics, spot weaknesses, and benchmark your performance against competitors efficiently.
  • Outbound link and partnership insights: Identify all external domains a site links to, helping you understand content strategy, partnerships, and potential link-building prospects.

Supported Tools & Triggers

Tools
Backlinks stats retrievalRetrieves comprehensive backlink statistics for a specified website or url using ahrefs' site explorer tool.
Batch Url AnalysisPerforms a batch analysis on multiple urls or domains using ahrefs' powerful seo metrics.
Domain rating for site explorerRetrieves the domain rating (dr) for a specified domain.
Domain rating historyRetrieves the historical domain rating (dr) data for a specified domain over time.
Explore keywords overviewRetrieves a comprehensive overview of keyword data from ahrefs' keywords explorer tool.
Explore keyword volume by countryRetrieves the search volume data for specified keywords across different countries using ahrefs' keywords explorer tool.
Explore linked domains of a siteRetrieves a list of external domains that the specified target website or url links to, using ahrefs' site explorer functionality.
Explore matching terms for keywordsThe keywords explorer matching terms endpoint retrieves a list of keyword phrases that match or contain the specified keyword from ahrefs' vast database.
Fetch all backlinksRetrieves a comprehensive list of backlinks for a specified website or url using ahrefs' site explorer tool.
Fetch broken backlinks dataRetrieves a list of broken backlinks for a specified website using ahrefs' site explorer tool.
Fetch competitors overviewRetrieves a comprehensive overview of competitor data in relation to keyword rankings and organic search performance.
Fetch rank tracker overviewThe getranktrackeroverview endpoint retrieves a comprehensive summary of keyword rankings and seo performance data from ahrefs' rank tracker tool.
Fetch site explorer referring domainsRetrieves a list of domains that have backlinks pointing to a specified target website.
Fetch total search volume historyRetrieves the historical total search volume data for specified keywords using ahrefs' site explorer tool.
Get serp overviewRetrieves a comprehensive overview of search engine results pages (serp) data for specified keywords or queries.
Get site audit projectsRetrieves a list of site audit projects associated with the authenticated ahrefs account.
Get site explorer country metricsRetrieves country-specific site explorer metrics for a given website from ahrefs.
Get site explorer linked anchors externalThe site-explorer-linked-anchors-external endpoint retrieves data about external anchor texts linking to a specified target website.
Get url rating historyRetrieves the historical url rating data for a specified url over time.
Linked anchors explorerRetrieves information about internal linked anchors for a specified website using the ahrefs api.
List best by external linksThe 'get best by external links' endpoint retrieves a list of pages from a specified website, ranked by the number of external links pointing to them.
Pages by traffic overviewRetrieves a list of pages from a specified website, ordered by their estimated organic search traffic.
Retrieve anchor dataRetrieves anchor text data for a specified website or url using ahrefs' site explorer tool.
Retrieve best by internal linksRetrieves data on the best-performing internal links within a specified website using ahrefs' site explorer feature.
Retrieve crawler ip rangesRetrieves the list of ip address ranges used by ahrefs' web crawler (ahrefsbot).
Retrieve organic competitorsThe getorganiccompetitors endpoint in the ahrefs api provides a comprehensive analysis of websites competing for organic search rankings with a specified target domain.
Retrieve organic keywordsRetrieves organic keywords data for a specified website using ahrefs' site explorer tool.
Retrieve outlinks statsRetrieves comprehensive statistics about outgoing links (outlinks) from a specified website using ahrefs' site explorer tool.
Retrieve paid pages dataRetrieves information about paid pages (ppc advertising) for a specified website using ahrefs' site explorer tool.
Retrieve public crawler ipsRetrieves a list of ip addresses currently used by ahrefsbot, ahrefs' web crawler.
Retrieve related termsThe keywords explorer related terms endpoint retrieves a list of related terms for a given keyword using ahrefs' extensive keyword database.
Retrieve site explorer keywords historyRetrieves historical keyword performance data for a specified website or domain using ahrefs' site explorer.
Retrieve site explorer metricsThe getsiteexplorermetrics endpoint retrieves comprehensive seo metrics for a specified website using ahrefs' site explorer tool.
Retrieve site explorer metrics historyRetrieves historical seo metrics data for a specified website over a given time period.
Retrieve site explorer pages historyThe get site explorer pages history endpoint retrieves historical data about specific pages or domains from ahrefs' site explorer.
Retrieve site explorer referring domains historyRetrieves the historical data of referring domains for a specified website or url over time.
Retrieve subscription limits and usageRetrieves detailed information about the current subscription limits and usage for an ahrefs account.
Retrieve top pages from site explorerRetrieves data about the top-performing pages of a specified website using ahrefs' site explorer tool.
Retrieve volume historyRetrieves the historical search volume data for a specified keyword using ahrefs' keywords explorer tool.
Search suggestions explorerRetrieves search suggestions for a given keyword or phrase using ahrefs' keywords explorer tool.

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: ["ahrefs"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Ahrefs 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 Ahrefs-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 Ahrefs 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 ahrefs, 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("\nđź‘‹ 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 Ahrefs 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 Ahrefs 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: ["ahrefs"],
  });

  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 ahrefs, 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("\nđź‘‹ Session ended.");
    process.exit(0);
  });
}

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

Conclusion

You've successfully built a Ahrefs 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 Ahrefs MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Ahrefs MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Ahrefs MCP with Claude Agent SDK

Google ADK

Google ADK

Use Ahrefs MCP with Google ADK

LangChain

LangChain

Use Ahrefs MCP with LangChain

Mastra AI

Mastra AI

Use Ahrefs MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Ahrefs MCP with LlamaIndex

CrewAI

CrewAI

Use Ahrefs MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Ahrefs 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 Ahrefs 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