SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Ahrefs MCP with LangChain

Connect LangChain to Ahrefs MCP. Get domain rating trend for competitor site, list all broken backlinks for your website, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Ahrefs logoAhrefs
Api KeyOauth2

Ahrefs is an SEO and marketing platform for site audits, keyword research, and competitor insights. It helps you improve search rankings and drive organic traffic.

46 Tools

Introduction

This guide walks you through connecting Ahrefs to LangChain using the Composio tool router. By the end, you'll have a working Ahrefs agent that can analyze backlinks and referring domains, research keywords and search volume, track domain rating, find organic competitors, and check top pages through natural language commands.

This guide will help you understand how to give your LangChain 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.

Also integrate Ahrefs with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKMuseCodexKimi CodeOpenClawHermesAtomic AgentCLIGoogle ADKVercel AI SDKMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Ahrefs project to Composio
  • Create a Tool Router MCP session for Ahrefs
  • Initialize an MCP client and retrieve Ahrefs tools
  • Build a LangChain agent that can interact with Ahrefs
  • Set up an interactive chat interface for testing

What is LangChain?

LangChain is a framework for developing applications powered by language models. It provides tools and abstractions for building agents that can reason, use tools, and maintain conversation context.

Key features include:

  • Agent Framework: Build agents that can use tools and make decisions
  • MCP Integration: Connect to external services through Model Context Protocol adapters
  • Memory Management: Maintain conversation history across interactions
  • Multi-Provider Support: Works with OpenAI, Anthropic, and other LLM providers

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 backlink, keyword, competitor, ranking, and search results data, so your agent can analyze backlinks, compare competitors, review keyword rankings, inspect search results, and discover keyword ideas on your behalf.

  • Backlink and anchor analysis: Have your agent retrieve backlinks, summarize backlink statistics, and examine the anchor text pointing to a website or URL.
  • Competitor research: Let the agent compare competitors based on keyword rankings and organic search performance.
  • Keyword ranking history: Direct your agent to review current rank tracking data and historical keyword performance for a website or domain.
  • Search results and keyword ideas: Instruct your agent to inspect search results for chosen queries and find related search suggestions for a keyword or phrase.
  • Outgoing links and crawler verification: Have your agent review outgoing link statistics for a website or retrieve AhrefsBot IP ranges for crawler verification.

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 step10 STEPS
1

Prerequisites

Before starting this tutorial, make sure you have:
  • Python 3.10 or higher installed on your system
  • A Composio account with an API key
  • An OpenAI API key
  • Basic familiarity with Python and async programming
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 dependencies

npm install @composio/langchain @langchain/core @langchain/openai @langchain/mcp-adapters dotenv

Install the required packages for LangChain with MCP support.

What's happening:

  • @composio/langchain provides Composio integration for LangChain
  • @langchain/mcp-adapters enables MCP client connections
  • @langchain/core is the core agent framework
  • dotenv/config loads environment variables
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_composio_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your requests to Composio's API
  • COMPOSIO_USER_ID identifies the user for session management
  • OPENAI_API_KEY enables access to OpenAI's language models
5

Import dependencies

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

dotenv.config();
What's happening:
  • We're importing LangChain's MCP adapter and Composio SDK
  • The dotenv/config import loads environment variables from your .env file
  • This setup prepares the foundation for connecting LangChain with Ahrefs functionality through MCP
6

Initialize Composio client

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.COMPOSIO_USER_ID;

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });
What's happening:
  • We're loading the COMPOSIO_API_KEY from environment variables and validating it exists
  • Creating a Composio instance that will manage our connection to Ahrefs tools
  • Validating that COMPOSIO_USER_ID is also set before proceeding
7

Create a Tool Router session

const session = await composio.create(
    userId as string,
    {
        toolkits: ['ahrefs']
    }
);

const url = 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 session.mcp.url is the MCP server URL that your agent will use
  • This approach allows the agent to dynamically load and use Ahrefs tools as needed
8

Configure the agent with the MCP URL

const client = new MultiServerMCPClient({
    "ahrefs-agent": {
        transport: "http",
        url: url,
        headers: {
            "x-api-key": process.env.COMPOSIO_API_KEY
        }
    }
});

const tools = await client.getTools();

const agent = createAgent({ model: "gpt-5", tools });
What's happening:
  • We're creating a MultiServerMCPClient that connects to our Ahrefs MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • getTools() retrieves all available Ahrefs tools that the agent can use
  • We're creating a LangChain agent using the GPT-5 model
9

Set up interactive chat interface

let conversationHistory: any[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log("Ask any Ahrefs related question or task to the agent.\n");

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

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;
    }

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

    const response = await agent.invoke({ messages: conversationHistory });
    conversationHistory = response.messages;

    const finalResponse = response.messages[response.messages.length - 1]?.content;
    console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\n👋 Session ended.');
        process.exit(0);
    });
What's happening:
  • We initialize an empty conversationHistory list to maintain context across interactions
  • A readline interface is used to continuously accept user input from the command line
  • When a user types a message, it's added to the conversation history and sent to the agent
  • The agent processes the request using the invoke() method with the full conversation history
  • Users can type 'exit', 'quit', or 'bye' to end the chat session gracefully
10

Run the application

main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});
What's happening:
  • We call the main() function to start the application

Complete Code

Here's the complete code to get you started with Ahrefs and LangChain:

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";  
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.COMPOSIO_USER_ID;

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });

    const session = await composio.create(
        userId as string,
        {
            toolkits: ['ahrefs']
        }
    );

    const url = session.mcp.url;
    
    const client = new MultiServerMCPClient({
        "ahrefs-agent": {
            transport: "http",
            url: url,
            headers: {
                "x-api-key": process.env.COMPOSIO_API_KEY
            }
        }
    });
    
    const tools = await client.getTools();
  
    const agent = createAgent({ model: "gpt-5", tools });
    
    let conversationHistory: any[] = [];
    
    console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
    console.log("Ask any Ahrefs related question or task to the agent.\n");
    
    const rl = readline.createInterface({
        input: process.stdin,
        output: process.stdout,
        prompt: 'You: '
    });

    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;
        }
        
        conversationHistory.push({ role: "user", content: trimmedInput });
        console.log("\nAgent is thinking...\n");
        
        const response = await agent.invoke({ messages: conversationHistory });
        conversationHistory = response.messages;
        
        const finalResponse = response.messages[response.messages.length - 1]?.content;
        console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\nSession ended.');
        process.exit(0);
    });
}

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

Conclusion

You've successfully built a LangChain agent that can interact with Ahrefs through Composio's Tool Router.

Key features of this implementation:

  • Dynamic tool loading through Composio's Tool Router
  • Conversation history maintenance for context-aware responses
  • Async Python provides clean, efficient execution of agent workflows
You can extend this further by adding error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
TOOLS

Supported Tools

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

Backlinks stats retrieval

Retrieves comprehensive backlink statistics for a specified website or URL using Ahrefs' Site Explorer tool.

Batch Url Analysis

Performs a batch analysis on multiple URLs or domains using Ahrefs' powerful SEO metrics.

Domain rating for site explorer

Retrieves Ahrefs Domain Rating and Ahrefs Rank for a specified domain or URL on a requested date.

Domain rating history

Retrieves the historical Domain Rating (DR) data for a specified domain over time.

Explore keywords overview

Retrieves keyword-level overview metrics from Ahrefs' Keywords Explorer for specified keywords or an existing keyword list in a country.

Explore keyword volume by country

Retrieves monthly search volume data across countries for a specified keyword using Ahrefs' Keywords Explorer.

Explore linked domains of a site

Retrieves a list of external domains that the specified target website or URL links to, using Ahrefs' Site Explorer functionality.

Explore matching terms for keywords

The keywords_explorer_matching_terms endpoint retrieves a list of keyword phrases that match or contain the specified keyword from Ahrefs' vast database.

Fetch all backlinks

Retrieves a comprehensive list of backlinks for a specified website or URL using Ahrefs' Site Explorer tool.

Fetch broken backlinks data

Retrieves a list of broken backlinks for a specified website using Ahrefs' Site Explorer tool.

Fetch competitors overview

Retrieves a Rank Tracker competitor overview for a project, including comparative keyword ranking and organic search performance data.

Fetch rank tracker overview

Retrieves an Ahrefs Rank Tracker overview for a project, date and device, with ranking and search-performance metrics.

Fetch site explorer referring domains

Retrieves a list of domains that have backlinks pointing to a specified target website.

Fetch total search volume history

Retrieves historical total search volume for keywords associated with a target domain or URL using Ahrefs Site Explorer.

Get content helper topics

Retrieve topics covered by top-ranking pages for a keyword.

Get domain rating free

Retrieve the free Ahrefs Domain Rating for a domain or URL.

Get domain rating top domains

Retrieves domains ordered by Ahrefs Domain Rating.

Get serp overview

Retrieves a SERP overview for one keyword in a specified country, optionally at a historical date.

Get site audit projects

Lists Site Audit projects associated with the authenticated Ahrefs account, with project and crawl status details.

Get site explorer AI responses count

Retrieve AI response citation and page counts for a site.

Get site explorer country metrics

Retrieves country-specific Site Explorer metrics for a target website or URL, including organic traffic and keyword metrics.

Get site explorer crawled pages

Retrieve crawled pages and crawl metadata for a target URL.

Get site explorer linked anchors external

Retrieves anchor text data for external links going out from a target website using Ahrefs Site Explorer.

Get url rating history

Retrieves the historical URL Rating data for a specified URL over time.

Linked anchors explorer

Retrieves information about internal linked anchors for a specified website using the Ahrefs API.

List best by external links

Retrieves pages from a specified website using Ahrefs' Site Explorer best-by-external-links report.

Pages by traffic overview

Retrieves a list of pages from a specified website, ordered by their estimated organic search traffic.

Post Domain Rating Free

Retrieve Domain Rating scores for up to 1,000 target URLs.

Retrieve anchor data

Retrieves anchor text data for a specified website or URL using Ahrefs' Site Explorer tool.

Retrieve best by internal links

Retrieves pages ranked by internal links for a specified website using Ahrefs' Site Explorer.

Retrieve crawler ip ranges

Retrieves the list of IP address ranges used by Ahrefs' web crawler (AhrefsBot).

Retrieve organic competitors

Retrieves organic search competitors for a target domain or URL, with keyword overlap and performance metrics.

Retrieve organic keywords

Retrieves organic keywords data for a specified website using Ahrefs' Site Explorer tool.

Retrieve outlinks stats

Retrieves outgoing-link statistics for a specified website or URL using Ahrefs Site Explorer.

Retrieve paid pages data

Retrieves information about paid pages (PPC advertising) for a specified website using Ahrefs' Site Explorer tool.

Retrieve public crawler ips

Retrieves a list of IP addresses currently used by AhrefsBot, Ahrefs' web crawler.

Retrieve related terms

Retrieves related keyword ideas for a given keyword or keyword list in a specified country.

Retrieve site explorer keywords history

Retrieves historical keyword performance data for a specified website or domain using Ahrefs' Site Explorer.

Retrieve site explorer metrics

Retrieves Site Explorer SEO metrics for a target domain or URL on a specified date, including backlink, referring-page and crawled-page counts.

Retrieve site explorer metrics history

Retrieves historical Site Explorer traffic metrics for a target website or URL over a specified period, including estimated organic and paid traffic and cost.

Retrieve site explorer pages history

Retrieves historical page counts for a target domain or URL from Ahrefs Site Explorer over a specified period.

Retrieve site explorer referring domains history

Retrieves the historical data of referring domains for a specified website or URL over time.

Retrieve subscription limits and usage

Retrieves an Ahrefs account's subscription limits and remaining API usage allowance.

Retrieve top pages from site explorer

Retrieves data about the top-performing pages of a specified website using Ahrefs' Site Explorer tool.

Retrieve volume history

Retrieves the historical search volume data for a specified keyword using Ahrefs' Keywords Explorer tool.

Search suggestions explorer

Retrieves search suggestions for keywords or an existing keyword list using Ahrefs Keywords Explorer.

FRAMEWORKS

How to build Ahrefs MCP Agent with another framework

Claude Code logo

Claude Code

Use Ahrefs MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Ahrefs MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Ahrefs MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Ahrefs MCP with Claude Agent SDK

Muse logo

Muse

Use Ahrefs MCP with Muse

Codex logo

Codex

Use Ahrefs MCP with Codex

Kimi Code logo

Kimi Code

Use Ahrefs MCP with Kimi Code

OpenClaw logo

OpenClaw

Use Ahrefs MCP with OpenClaw

Hermes logo

Hermes

Use Ahrefs MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Ahrefs MCP with Atomic Agent

CLI logo

CLI

Use Ahrefs MCP with CLI

Google ADK logo

Google ADK

Use Ahrefs MCP with Google ADK

Vercel AI SDK logo

Vercel AI SDK

Use Ahrefs MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Ahrefs MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Ahrefs MCP with LlamaIndex

CrewAI logo

CrewAI

Use Ahrefs MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Ahrefs MCP with Pydantic AI

AutoGen logo

AutoGen

Use Ahrefs MCP with AutoGen

FAQ

Frequently asked questions

Start with Ahrefs.It takes 30 seconds.

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

Start building