# How to integrate Google cloud vision MCP with OpenAI Agents SDK

```json
{
  "title": "How to integrate Google cloud vision MCP with OpenAI Agents SDK",
  "toolkit": "Google cloud vision",
  "toolkit_slug": "google_cloud_vision",
  "framework": "OpenAI Agents SDK",
  "framework_slug": "open-ai-agents-sdk",
  "url": "https://composio.dev/toolkits/google_cloud_vision/framework/open-ai-agents-sdk",
  "markdown_url": "https://composio.dev/toolkits/google_cloud_vision/framework/open-ai-agents-sdk.md",
  "updated_at": "2026-05-12T10:13:40.623Z"
}
```

## Introduction

This guide walks you through connecting Google cloud vision to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Google cloud vision agent that can bulk import product images from gcs csv, list all vision ai service locations, create a new product for image recognition through natural language commands.
This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Google cloud vision account through Composio's Google cloud vision MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Google cloud vision with

- [ChatGPT](https://composio.dev/toolkits/google_cloud_vision/framework/chatgpt)
- [Claude Agent SDK](https://composio.dev/toolkits/google_cloud_vision/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/google_cloud_vision/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/google_cloud_vision/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/google_cloud_vision/framework/codex)
- [Cursor](https://composio.dev/toolkits/google_cloud_vision/framework/cursor)
- [VS Code](https://composio.dev/toolkits/google_cloud_vision/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/google_cloud_vision/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/google_cloud_vision/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/google_cloud_vision/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/google_cloud_vision/framework/cli)
- [Google ADK](https://composio.dev/toolkits/google_cloud_vision/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/google_cloud_vision/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/google_cloud_vision/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/google_cloud_vision/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/google_cloud_vision/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/google_cloud_vision/framework/crew-ai)

## 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 Google cloud vision
- Configure an AI agent that can use Google cloud vision as a tool
- Run a live chat session where you can ask the agent to perform Google cloud vision 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 Google cloud vision MCP server, and what's possible with it?

The Google cloud vision MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Google Cloud Vision account. It provides structured and secure access to your image analysis resources, so your agent can perform actions like registering products, managing reference images, listing endpoints, and automating large-scale image operations on your behalf.
- Product and reference image management: Easily create new products and add reference images for visual search, enabling your agent to organize and expand your vision datasets effortlessly.
- Bulk import and product set operations: Let your agent import large numbers of reference images into product sets from Cloud Storage CSV files, streamlining dataset curation at scale.
- Automated product cleanup and deletion: Direct your agent to purge unused or orphan products from your project, keeping your cloud resources tidy without manual effort.
- Location and endpoint discovery: Quickly list available Vision AI service locations and existing IndexEndpoints, making it easy for your agent to select optimal regions and manage deployment targets.
- Vision API operation tracking: Retrieve and review ongoing or past Vision API operations, so your agent can monitor processing jobs and ensure workflow transparency.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `GOOGLE_CLOUD_VISION_ANNOTATE_FILES` | Annotate Files with Vision API | Tool to perform image detection and annotation for batch files in Google Cloud Vision. Supports PDF, TIFF, and GIF files. Extracts up to 5 frames (GIF) or pages (PDF/TIFF) from each file and performs detection for each image. Use when you need to analyze documents or multi-page images with features like text detection, label detection, face detection, or other Vision API capabilities. |
| `GOOGLE_CLOUD_VISION_ANNOTATE_FILES_ASYNC_BATCH` | Async Batch Annotate Files | Tool to run asynchronous image detection and annotation for a list of generic files (PDF, TIFF, GIF). Use when processing multi-page documents that may contain multiple images per page. Results are written to Google Cloud Storage and progress can be tracked via the returned operation name using VisionGetOperation. |
| `GOOGLE_CLOUD_VISION_ANNOTATE_IMAGES` | Annotate Images | Run image detection and annotation for a batch of images using Google Cloud Vision API. Performs various types of image analysis including face detection, landmark detection, logo detection, label detection, text detection (OCR), safe search detection, image properties, crop hints, web detection, product search, and object localization. Supports up to 16 images in a single batch request. Each image can have multiple feature types analyzed simultaneously. |
| `GOOGLE_CLOUD_VISION_ANNOTATE_IMAGES_ASYNC_BATCH` | Annotate Images Async Batch | Tool to run asynchronous image detection and annotation for a batch of images. Use when processing multiple images or large images that require longer processing time. Results are written to Google Cloud Storage as JSON files. |
| `GOOGLE_CLOUD_VISION_ANNOTATE_LOCATION_IMAGES` | Annotate Location Images | Tool to run image detection and annotation for a batch of images scoped to a specific project and location. Performs various types of image analysis including label detection, face detection, landmark detection, logo detection, OCR text detection, safe search detection, image properties, crop hints, web detection, product search, and object localization. Supports processing up to 16 images per request with regional endpoint routing (us, asia, eu). Use this when you need to analyze images with location-specific processing for content extraction, text recognition, object detection, face identification, or landmark/logo recognition. |
| `GOOGLE_CLOUD_VISION_CREATE_PRODUCT` | Create Vision Product | Creates a new Product resource in Google Cloud Vision Product Search. A Product represents a physical item that can be visually searched using reference images. After creating a product, you can add reference images to it and include it in product sets for visual search capabilities. Prerequisites: - Vision API must be enabled in your Google Cloud project - Product Search must be enabled - Valid project ID and location (us-west1, us-east1, europe-west1, or asia-east1) Use this action to: - Register a new product for visual search - Set up product metadata (display name, description, category, labels) - Obtain a product resource name for adding reference images |
| `GOOGLE_CLOUD_VISION_CREATE_PRODUCT_SET` | Create Product Set | Creates a new ProductSet resource in Google Cloud Vision Product Search. A ProductSet is a container for grouping related products together for visual search. After creating a product set, you can add products to it using the AddProductToProductSet action. Prerequisites: - Vision API must be enabled in your Google Cloud project - Product Search must be enabled - Valid project ID and location (us-west1, us-east1, europe-west1, or asia-east1) Use this action to: - Create a new product set container - Organize products into logical groups - Obtain a product set resource name for adding products |
| `GOOGLE_CLOUD_VISION_CREATE_REFERENCE_IMAGE` | Create ReferenceImage | Tool to create a ReferenceImage under a product. Use when adding a new image to a product for detection. |
| `GOOGLE_CLOUD_VISION_DELETE_PRODUCT` | Delete Product | Permanently deletes a Product and its associated reference images from Google Cloud Vision API. This is a destructive operation that cannot be undone. The product metadata and all images are deleted immediately, though search queries against ProductSets may temporarily return cached results until caches refresh. Use this tool when you need to remove a product that is no longer needed. Ensure you have the correct product resource name before deletion. |
| `GOOGLE_CLOUD_VISION_GET_PRODUCT` | Get Product | Tool to get information associated with a Product. Use when you have the product resource name and need its details. |
| `GOOGLE_CLOUD_VISION_GET_PRODUCT_SET` | Get Product Set | Tool to get a ProductSet. Use when you need metadata details of an existing ProductSet by its full resource name. Use after obtaining the resource name. |
| `GOOGLE_CLOUD_VISION_IMPORT_PRODUCT_SETS` | Import Product Sets | Asynchronously imports product sets and reference images from a CSV file stored in Google Cloud Storage. This bulk import operation creates ProductSets, Products, and ReferenceImages from a properly formatted CSV file. Returns a long-running Operation that can be polled for completion status. The import automatically creates new ProductSets and Products if they don't exist based on the IDs in the CSV. Use this when you need to: - Bulk import multiple products and images at once - Create product catalogs from existing CSV data - Set up initial product search datasets Note: Requires OAuth authentication with cloud-platform or cloud-vision scope, and read access to the GCS bucket. |
| `GOOGLE_CLOUD_VISION_LIST_INDEX_ENDPOINTS` | List Vision AI IndexEndpoints | Lists IndexEndpoints in Vertex AI Vision for a given project and location. IndexEndpoints are deployed instances of image indexes used for visual search and retrieval in Vision AI's media warehouse. Use this tool to discover existing endpoints before querying them or to manage deployed indexes. IMPORTANT: Requires OAuth2 authentication (API keys are NOT supported). Needs 'visionai.indexEndpoints.list' IAM permission. |
| `GOOGLE_CLOUD_VISION_LIST_LOCATIONS` | List Locations | Tool to list available Vision AI service locations for a project. Use when you need to discover supported regions before making region-specific API calls. |
| `GOOGLE_CLOUD_VISION_LIST_OPERATIONS` | List Vision API Operations | Tool to list operations that match the specified filter. Use when you need to retrieve all operations under a specific project and location. |
| `GOOGLE_CLOUD_VISION_PURGE_PRODUCTS` | Purge Products | Tool to asynchronously delete products in a ProductSet or orphan products. Use when you need to clean up products at scale; ensure `force` is true to execute. |
| `GOOGLE_CLOUD_VISION_UPDATE_PRODUCT` | Update Product | Tool to update a Product's mutable fields: displayName, description, and productLabels. Use after confirming the product resource name. |
| `GOOGLE_CLOUD_VISION_UPDATE_PRODUCT_SET` | Update Product Set | Tool to update a ProductSet resource. Use when you need to modify the displayName of an existing ProductSet. |
| `GOOGLE_CLOUD_VISION_VISION_ADD_PRODUCT_TO_PRODUCT_SET` | Add Product to ProductSet | Add a Product to a ProductSet in Google Cloud Vision Product Search. This action associates a Product with a ProductSet, enabling the product to be included in product search queries against that set. Both resources must exist in the same Google Cloud project and location before calling this action. Key characteristics: - Idempotent: If the Product is already in the ProductSet, no change is made and no error occurs - Constraint: One Product can be added to at most 100 ProductSets - The Product and ProductSet must be in the same project and location - Valid locations: us-west1, us-east1, europe-west1, asia-east1 Use this after creating both a Product and a ProductSet to establish their association. Returns an empty response on success. |
| `GOOGLE_CLOUD_VISION_VISION_CANCEL_OPERATION` | Cancel Vision Operation | Starts asynchronous cancellation of a long-running Vision API operation. Returns an empty response on successful cancellation request. Note that the server makes a best effort to cancel the operation, but success is not guaranteed. Use the Get Operation action to check if cancellation succeeded or if the operation completed despite the cancellation attempt. The server may return UNIMPLEMENTED if the operation does not support cancellation. |
| `GOOGLE_CLOUD_VISION_VISION_DELETE_OPERATION` | Delete Vision API Operation | Tool to delete a long-running Vision API operation. Use after confirming the operation name. |
| `GOOGLE_CLOUD_VISION_VISION_DELETE_PRODUCT_SET` | Delete Product Set | Tool to permanently delete a ProductSet. Use after confirming the ProductSet's resource name. |
| `GOOGLE_CLOUD_VISION_VISION_DELETE_REFERENCE_IMAGE` | Delete Reference Image | Permanently removes a reference image from a product in Google Cloud Vision Product Search. This action deletes the reference image association from the specified product. The image will be marked for deletion and removed during the next indexing operation. Note that the actual image file in Google Cloud Storage is not deleted. Use this when you need to: - Remove outdated or incorrect product reference images - Clean up test images from products - Update product imagery by removing old references Prerequisites: - The product must exist - The reference image must have been previously created under the product - You need the full resource path of the reference image (use List Reference Images if unknown) |
| `GOOGLE_CLOUD_VISION_VISION_GET_OPERATION` | Get Vision API Operation | Retrieves the latest state of a long-running Vision API operation. Use this to poll the status of asynchronous operations like importProductSets or purgeProducts. The operation name is returned when you start an async operation. |
| `GOOGLE_CLOUD_VISION_VISION_GET_REFERENCE_IMAGE` | Get Reference Image | Tool to get information associated with a ReferenceImage. Use when you have the full resource name and need its metadata. |
| `GOOGLE_CLOUD_VISION_VISION_LIST_PRODUCTS_IN_PRODUCT_SET` | List Products in ProductSet | Tool to list Products in a specified ProductSet. Use when you need to retrieve Products associated with a ProductSet after confirming it exists, with optional pagination. |
| `GOOGLE_CLOUD_VISION_VISION_LIST_PROJECTS` | List Projects | List Google Cloud projects accessible to the authenticated user via Cloud Resource Manager API. This action queries the Cloud Resource Manager API (not Vision API directly) to enumerate projects. It requires OAuth 2.0 authentication - API key auth is insufficient. Use this when you need to discover available project IDs before making Vision API calls that require project identifiers. Note: Returns projects you have 'resourcemanager.projects.get' permission on. |
| `GOOGLE_CLOUD_VISION_VISION_LIST_REFERENCE_IMAGES` | List Reference Images | Tool to list reference images for a product. Use when you need to retrieve stored reference images under a specified product resource name, with optional pagination. |
| `GOOGLE_CLOUD_VISION_VISION_REMOVE_PRODUCT_FROM_PRODUCT_SET` | Remove Product from ProductSet | Removes a Product from a specified ProductSet in Google Cloud Vision API. This operation unlinks a product from a product set but does not delete either resource. Both the product and product set must exist in the same Google Cloud project and location. The product must have been previously added to the product set for this operation to succeed. Use this when you need to reorganize products across product sets or remove a product from a set without deleting the product itself. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Google cloud vision MCP server is an implementation of the Model Context Protocol that connects your AI agent to Google cloud vision. It provides structured and secure access so your agent can perform Google cloud vision operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before starting, make sure you have:
- Composio API Key and OpenAI API Key
- Primary know-how of OpenAI Agents SDK
- A live Google cloud vision project
- Some knowledge of Python or Typescript

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Go to Settings and copy your API key.

### 2. Install dependencies

Install the Composio SDK and the OpenAI Agents SDK.
```python
pip install composio_openai_agents openai-agents python-dotenv
```

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

### 3. Set up environment variables

Create a .env file and add your OpenAI and Composio API keys.
```bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com
```

### 4. Import dependencies

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 Google cloud vision.
```python
import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
```

```typescript
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';
```

### 5. Set up the Composio instance

No description provided.
```python
load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
```

```typescript
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(),
});
```

### 6. Create a Tool Router session

What is happening:
- You give the Tool Router the user id and the toolkits you want available. Here, it is only google_cloud_vision.
- The router checks the user's Google cloud vision connection and prepares the MCP endpoint.
- The returned session.mcp.url is the MCP URL that your agent will use to access Google cloud vision.
- This approach keeps things lightweight and lets the agent request Google cloud vision tools only when needed during the conversation.
```python
# Create a Google cloud vision Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["google_cloud_vision"]
)

mcp_url = session.mcp.url
```

```typescript
// Create Tool Router session for Google cloud vision
const session = await composio.create(userId as string, {
  toolkits: ['google_cloud_vision'],
});
const mcpUrl = session.mcp.url;
```

### 7. Configure the agent

No description provided.
```python
# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Google cloud vision. "
        "Help users perform Google cloud vision operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
```

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

### 8. Start chat loop and handle conversation

No description provided.
```python
print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
```

```typescript
// 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);
});
```

## Complete Code

```python
import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["google_cloud_vision"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Google cloud vision. "
        "Help users perform Google cloud vision operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
```

```typescript
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: ['google_cloud_vision'],
  });
  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 Google cloud vision. Help users perform Google cloud vision 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 Google cloud vision MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Google cloud vision.
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.

## How to build Google cloud vision MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/google_cloud_vision/framework/chatgpt)
- [Claude Agent SDK](https://composio.dev/toolkits/google_cloud_vision/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/google_cloud_vision/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/google_cloud_vision/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/google_cloud_vision/framework/codex)
- [Cursor](https://composio.dev/toolkits/google_cloud_vision/framework/cursor)
- [VS Code](https://composio.dev/toolkits/google_cloud_vision/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/google_cloud_vision/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/google_cloud_vision/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/google_cloud_vision/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/google_cloud_vision/framework/cli)
- [Google ADK](https://composio.dev/toolkits/google_cloud_vision/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/google_cloud_vision/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/google_cloud_vision/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/google_cloud_vision/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/google_cloud_vision/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/google_cloud_vision/framework/crew-ai)

## Related Toolkits

- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.
- [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.
- [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.
- [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.
- [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application.
- [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities.
- [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization.
- [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications.
- [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations.
- [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key.
- [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient.
- [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions.
- [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences.
- [Chatbotkit](https://composio.dev/toolkits/chatbotkit) - Chatbotkit is a platform for building and managing AI-powered chatbots using robust APIs and SDKs. It lets you easily add conversational AI to your apps for better user engagement.
- [Cody](https://composio.dev/toolkits/cody) - Cody is an AI assistant built for businesses, trained on your company's knowledge and data. It delivers instant answers and insights, tailored for your team.
- [Context7 MCP](https://composio.dev/toolkits/context7_mcp) - Context7 MCP delivers live, version-specific code docs and examples right from the source. It helps developers and AI agents instantly retrieve authoritative programming info—no more out-of-date docs.
- [Customgpt](https://composio.dev/toolkits/customgpt) - CustomGPT.ai lets you build and deploy chatbots tailored to your own data and business needs. Get precise and context-aware AI conversations without writing code.
- [Datarobot](https://composio.dev/toolkits/datarobot) - Datarobot is a machine learning platform that automates model development, deployment, and monitoring. It empowers organizations to quickly gain predictive insights from large datasets.
- [Deepgram](https://composio.dev/toolkits/deepgram) - Deepgram is an AI-powered speech recognition platform for accurate audio transcription and understanding. It enables fast, scalable speech-to-text with advanced audio intelligence features.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Google cloud vision MCP?

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

### Can I use Tool Router MCP with OpenAI Agents SDK?

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 Google cloud vision tools.

### Can I manage the permissions and scopes for Google cloud vision while using Tool Router?

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

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)