How to integrate Cloudinary MCP with LlamaIndex

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Cloudinary Logo
LlamaIndex Logo
divider

Introduction

This guide walks you through connecting Cloudinary to LlamaIndex using the Composio tool router. By the end, you'll have a working Cloudinary agent that can create a new folder for event photos, delete derived assets with ids [123,456], set up upload preset with watermarking, remove unused metadata field 'old_tag' through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Cloudinary account through Composio's Cloudinary 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:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Cloudinary
  • Connect LlamaIndex to the Cloudinary MCP server
  • Build a Cloudinary-powered agent using LlamaIndex
  • Interact with Cloudinary through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

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

The Cloudinary MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Cloudinary account. It provides structured and secure access to your digital asset management system, so your agent can perform actions like organizing folders, creating metadata fields, managing upload presets, and handling asset deletion on your behalf.

  • Automated folder and asset organization: Easily instruct your agent to create new asset folders or remove empty ones, keeping your Cloudinary library tidy and structured.
  • Metadata management: Let your agent create custom metadata fields or delete obsolete ones, extending and refining your asset tagging and search capabilities.
  • Preset and upload mapping creation: Have your agent set up upload presets with specific options or define dynamic folder mappings, automating consistent upload processes across your assets.
  • Resource and derived asset cleanup: Direct your agent to permanently delete assets by ID or remove unnecessary derived resources, ensuring your storage stays efficient and clutter-free.
  • Datasource entry management: Ask your agent to inactivate or delete specific datasource entries from metadata fields, keeping your metadata schema accurate and up to date.

Supported Tools & Triggers

Tools
Create FolderTool to create a new asset folder.
Create Metadata FieldTool to create a new metadata field definition.
Create TriggerTool to create a new webhook trigger for a specified event type.
Create Upload MappingTool to create a new upload mapping folder and url template.
Create Upload PresetTool to create a new upload preset.
Delete Derived ResourcesTool to delete derived assets.
Delete Metadata Field Datasource EntriesTool to delete datasource entries for a specified metadata field.
Delete FolderTool to delete an empty asset folder.
Delete Metadata FieldTool to delete a metadata field by external id.
Delete Resources by Asset IDTool to delete resources by asset ids.
Delete Resources by TagsTool to delete cloudinary assets by tag.
Delete TriggerTool to delete a trigger (webhook notification).
Get Adaptive Streaming ProfilesTool to list adaptive streaming profiles.
Get product environment config detailsTool to get product environment config details.
Get Metadata Field By IDTool to get a single metadata field definition by external id.
Get Resource by Asset IDGet resource by asset id
Get Resource by Public IDTool to get details of a single resource by public id.
Get Resources by Asset FolderTool to list assets stored directly in a specified folder.
Get Resources by ContextTool to retrieve assets with a specified contextual metadata key/value.
Get Resources in ModerationTool to retrieve assets in a moderation queue by status.
Get Root FoldersTool to list all root folders in the product environment.
Get Streaming Profile DetailsTool to get details of a single streaming profile by name.
Get Resource TagsTool to list all tags used for a specified resource type.
Get TransformationsTool to list all transformations (named and unnamed).
List Webhook TriggersTool to list all webhook triggers for event types in your environment.
Get Upload Mapping DetailsTool to retrieve details of a single upload mapping by folder.
Get Upload MappingsTool to list all upload mappings by folder.
Get UsageTool to get product environment usage details.
Order Metadata Field DatasourceTool to update ordering of a metadata field datasource.
Ping Cloudinary ServersTool to ping cloudinary servers.
Restore Metadata Field Datasource EntriesTool to restore previously deleted datasource entries for a metadata field.
Search FoldersTool to search asset folders with filtering, sorting, and pagination.
Update FolderTool to rename or move an existing asset folder.
Update Metadata FieldTool to update a metadata field definition by external id.

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:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Cloudinary account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Cloudinary

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Cloudinary access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called cloudinary_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["cloudinary"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Cloudinary actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Cloudinary actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, cloudinary)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Cloudinary tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Cloudinary database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Cloudinary

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Cloudinary, then start asking questions.

Complete Code

Here's the complete code to get you started with Cloudinary and LlamaIndex:

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["cloudinary"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Cloudinary actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Cloudinary actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Cloudinary to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Cloudinary tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Cloudinary MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Cloudinary MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Cloudinary MCP with Claude Agent SDK

Google ADK

Google ADK

Use Cloudinary MCP with Google ADK

LangChain

LangChain

Use Cloudinary MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Cloudinary MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Cloudinary MCP with Mastra AI

CrewAI

CrewAI

Use Cloudinary MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex 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 Cloudinary tools.

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

Yes, absolutely. You can configure which Cloudinary 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 Cloudinary 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