How to integrate Keyword MCP with OpenAI Agents SDK

This guide walks you through connecting Keyword to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Keyword agent that can track keyword rankings for target domains, compare seo visibility across competitors, find ranking drops for tracked keywords through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Keyword account through Composio's Keyword MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Keyword logoKeyword
Api Key

Keyword.com is a digital marketing platform for search rank tracking and SEO analytics. Use it to monitor keyword performance, spot ranking changes, and measure SEO visibility.

20 Tools

Introduction

This guide walks you through connecting Keyword to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Keyword agent that can track keyword rankings for target domains, compare seo visibility across competitors, find ranking drops for tracked keywords through natural language commands.

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

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

Also integrate Keyword with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Keyword
  • Configure an AI agent that can use Keyword as a tool
  • Run a live chat session where you can ask the agent to perform Keyword operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The Keyword MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Keyword account. It provides structured and secure access to your SEO projects, keywords, rankings, and performance data, so your agent can monitor search rankings, analyze keyword movement, review top pages, track share of voice, and manage keyword settings on your behalf.

  • Keyword ranking analysis: Have your agent retrieve tracked keywords, review their current ranking metrics, and examine up to 180 days of Google ranking history.
  • Project performance monitoring: Let the agent summarize active projects, inspect project details, and analyze keyword movement across projects, groups, or tags.
  • Share of voice and page insights: Direct your agent to track share of voice over time and identify top ranking pages by keyword count, average rank, search volume, and cost per click.
  • Alerts and regional tracking: Instruct your agent to review account alerts and list the Google regions tracked for each project.
  • Keyword and project management: Have your agent update keyword settings, refresh rankings on demand, or delete keywords and projects you no longer need.

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 starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Keyword project
  • Some knowledge of Python or Typescript
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
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Keyword.
6

Set up the Composio instance

dotenv.config();

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

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Keyword
const session = await composio.create(userId as string, {
  toolkits: ['keyword'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only keyword.
  • The router checks the user's Keyword connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Keyword.
  • This approach keeps things lightweight and lets the agent request Keyword tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Keyword. Help users perform Keyword operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Keyword and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Keyword operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

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

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Keyword.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Keyword and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

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

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['keyword'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Keyword. Help users perform Keyword operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

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

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\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

This was a starter code for integrating Keyword MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Keyword.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

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

Add Keywords

Tool to add keywords to a Keyword.

Archive Project

Tool to archive a project in Keyword.

Create Project or Group

Tool to create a new project or group in Keyword.

Delete Keyword

Tool to delete a single keyword from a project or group.

Bulk delete keywords

Tool to bulk delete multiple keywords from a single project by providing keyword IDs.

Delete Project

Tool to delete a single project or group from Keyword.

Get Current User

Tool to retrieve the current authenticated user's account information.

Get Keyword

Tool to retrieve all keyword settings and ranking metrics for a single keyword.

Get Project Details

Tool to retrieve a single project's summary from Keyword.

Get Project Metrics

Retrieve keyword movement metrics for a project, group, or tag.

Get Keyword Ranking History

Tool to retrieve Google ranking history for specified keywords for up to 180 days.

Get Share of Voice History

Retrieve Share of Voice data over time for a specific project.

Get Top Pages

Tool to retrieve Top Pages data for a project showing ranking URLs with keyword counts, average rank, search volume, and cost per click metrics.

List Active Projects

Tool to retrieve all active projects with their groups, tags, and keyword counts.

List Alerts

Tool to retrieve all alerts for the Keyword.

List Keywords

Tool to retrieve all keywords and their ranking data in a project or group.

List Project Regions

Tool to list all Google regions being tracked in a Keyword.

Refresh Keywords

Tool to trigger an on-demand update for all keywords in one or more projects or groups.

Restore Archived Project

Tool to restore an archived project or group.

Update Keywords

Tool to update keyword settings in a project.

FAQ

Frequently asked questions

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

Yes, you can. OpenAI Agents 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 Keyword tools.

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

Start with Keyword.It takes 30 seconds.

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

Start building