# How to integrate Docker hub MCP with LlamaIndex

```json
{
  "title": "How to integrate Docker hub MCP with LlamaIndex",
  "toolkit": "Docker hub",
  "toolkit_slug": "docker_hub",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/docker_hub/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/docker_hub/framework/llama-index.md",
  "updated_at": "2026-05-12T10:09:03.978Z"
}
```

## Introduction

This guide walks you through connecting Docker hub to LlamaIndex using the Composio tool router. By the end, you'll have a working Docker hub agent that can create a new docker hub repository, add a member to your docker organization, delete an old image from a repository through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Docker hub account through Composio's Docker hub MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Docker hub with

- [OpenAI Agents SDK](https://composio.dev/toolkits/docker_hub/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/docker_hub/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/docker_hub/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/docker_hub/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/docker_hub/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/docker_hub/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/docker_hub/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/docker_hub/framework/cli)
- [Google ADK](https://composio.dev/toolkits/docker_hub/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/docker_hub/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/docker_hub/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/docker_hub/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/docker_hub/framework/crew-ai)

## 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 Docker hub
- Connect LlamaIndex to the Docker hub MCP server
- Build a Docker hub-powered agent using LlamaIndex
- Interact with Docker hub 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 Docker hub MCP server, and what's possible with it?

The Docker hub MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Docker Hub account. It provides structured and secure access to your container repositories and organizations, so your agent can perform actions like creating repositories, managing organization members, deleting images, setting up webhooks, and cleaning up tags on your behalf.
- Repository and image management: Let your agent create new Docker Hub repositories, delete existing ones, and remove specific images or tags as needed.
- Organization and team automation: Easily add members to organizations, create new Docker Hub organizations, or delete organizations and teams directly from your workflows.
- Webhook configuration: Set up or remove repository webhooks to automate external integrations and keep your CI/CD pipelines in sync.
- Tag and resource cleanup: Direct your agent to delete outdated tags or unused resources, helping you maintain a tidy container registry.
- Secure role management: Invite users with specific roles to your organizations, ensuring the right access for collaborators and teams.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `DOCKER_HUB_ADD_ORG_MEMBER` | Add Organization Member | Invite a user to join a Docker Hub organization. Sends an invitation email to the specified user (by Docker ID or email). The user must accept the invitation to become a member. Requires owner or admin privileges on the target organization. |
| `DOCKER_HUB_CREATE_ORGANIZATION` | Create Docker Hub Organization | Create a new Docker Hub organization. Note: This endpoint requires JWT authentication obtained via /v2/users/login and may have restricted access. |
| `DOCKER_HUB_CREATE_REPOSITORY` | Create Docker Hub Repository | Creates a new Docker Hub repository under the specified namespace. Use this to programmatically create public or private repositories for storing Docker images. Requires proper authentication with write permissions to the namespace. |
| `DOCKER_HUB_CREATE_WEBHOOK` | Create Docker Hub Webhook | Create a webhook on a Docker Hub repository to receive notifications on image push events. This is a two-step process: 1. Create the webhook with a name 2. Add a hook URL to the webhook Requires admin permissions on the repository. |
| `DOCKER_HUB_DELETE_IMAGE` | Delete Repository Images | Delete one or more images from your Docker Hub namespace using the bulk delete API. IMPORTANT REQUIREMENTS: - You must own the namespace (your username or an organization you admin) - You cannot delete images from 'library' (official Docker images) - Images are identified by SHA256 digest (get from LIST_IMAGES action) USAGE: 1. First use LIST_IMAGES to get image digests for your repository 2. Then call this action with the namespace, repository, and digest(s) Example: DELETE_IMAGE( namespace="myusername", manifests=[{"repository": "myapp", "digest": "sha256:abc123..."}] ). WARNING: Deletion is permanent and irreversible — obtain explicit user confirmation before calling this action. |
| `DOCKER_HUB_DELETE_ORGANIZATION` | Delete Docker Hub Organization | Permanently deletes a Docker Hub organization. Requires owner permissions on the organization. This action is idempotent - deleting a non-existent organization returns success (404 treated as success). WARNING: Deletion is irreversible and removes all associated repositories, teams, and members. |
| `DOCKER_HUB_DELETE_REPOSITORY` | Delete Docker Hub Repository | Permanently deletes a Docker Hub repository and all its images/tags. WARNING: This action is irreversible. All images, tags, and metadata will be permanently removed. This operation is idempotent - deleting a non-existent repository returns success. You must have admin/owner permissions on the repository to delete it. |
| `DOCKER_HUB_DELETE_TAG` | Delete Repository Tag | Permanently delete a specific tag from a Docker Hub repository. Requirements: - Must have write/admin access to the repository - The namespace must be your username or an organization you belong to - This action is irreversible - the tag will be permanently removed Note: Cannot delete tags from official Docker Hub images (library namespace). |
| `DOCKER_HUB_DELETE_TEAM` | Delete Docker Hub Team | Permanently deletes a team from a Docker Hub organization. This operation is idempotent - deleting a non-existent team will succeed silently. Requires organization admin permissions. Use DOCKER_HUB_LIST_TEAMS to find available teams before deletion. |
| `DOCKER_HUB_DELETE_WEBHOOK` | Delete Docker Hub repository webhook | Deletes a specific webhook from a Docker Hub repository. Use this tool to remove webhook configurations from repositories you own or have admin access to. This is useful for cleaning up outdated, misconfigured, or no longer needed webhooks. Prerequisites: - You must have admin access to the repository - The repository and webhook must exist - Use the list webhooks action first to get the webhook ID Returns a success message if the webhook was deleted, or an error if the webhook doesn't exist or you lack permission to delete it. |
| `DOCKER_HUB_GET_IMAGE` | Get Docker Hub Image | Retrieve details about a specific platform-specific image variant by its digest. This tool searches through repository tags to find and return metadata for an image matching the specified SHA256 digest. Returns architecture, OS, size, status, and timestamps. Use LIST_IMAGES first to discover available digests, then use this tool to get details about a specific image variant. Example: GET_IMAGE(namespace="library", repository="ubuntu", digest="sha256:a4453623f2f8319cfff65c43da9be80fe83b1a7ce689579b475867d69495b782") |
| `DOCKER_HUB_GET_REPOSITORY` | Get Docker Hub Repository | Retrieves detailed information about a specific Docker Hub repository. Use this to get repository metadata including description, star/pull counts, permissions, and configuration. Works with both public and private repositories (authentication required for private repos). |
| `DOCKER_HUB_GET_TAG` | Get Docker Hub Tag | Tool to retrieve details of a specific Docker Hub repository tag. Use after confirming the namespace, repository, and tag name. |
| `DOCKER_HUB_GET_TEAM` | Get Docker Hub Team | Retrieve details of a specific team (group) within a Docker Hub organization. Returns the team's ID, name, and description. Requires organization membership with appropriate permissions to view team details. |
| `DOCKER_HUB_GET_WEBHOOK` | Get Docker Hub Webhook | Retrieves details of a specific Docker Hub webhook by its ID. Use this tool when you need to inspect an existing webhook's configuration, including its target URL, configured events, and active status. You must have admin or write access to the repository to retrieve webhook details. Prerequisites: - You must have admin or write access to the repository - The webhook ID must exist (can be obtained from the list webhooks action) Returns the webhook's ID, name, target URL, events, active status, and timestamps. |
| `DOCKER_HUB_LIST_ORG_ACCESS_TOKENS` | List Organization Access Tokens | Tool to list all organization access tokens for a Docker Hub organization. Use when you need to view or audit access tokens associated with an organization. Requires appropriate organization permissions to view tokens. |
| `DOCKER_HUB_LIST_ORGANIZATIONS` | List Docker Hub Organizations | List Docker Hub organizations that the authenticated user belongs to. Returns a paginated list of organizations with details like name, company, and badge status; some metadata fields may be absent — use org name for follow-up detail calls when complete metadata is required. An empty result is valid and indicates the user belongs to no organizations. Use this to discover which organizations a user has access to before performing org-specific operations. |
| `DOCKER_HUB_LIST_ORG_MEMBERS` | List Docker Hub Organization Members | Lists members of a Docker Hub organization with their roles and details. Use this tool to: - Audit organization membership - View member roles (owner, member) - Check team assignments for members - Export organization member lists Requirements: - You must have access to the organization (owner or member role) - Authentication via Personal Access Token (PAT) which is exchanged for JWT Note: This endpoint requires organization-level access and proper authentication. |
| `DOCKER_HUB_LIST_REPOSITORIES` | List Docker Hub Repositories | Tool to list repositories under a namespace. Use when you need to enumerate repositories within a specific Docker Hub namespace, with optional filtering and pagination. |
| `DOCKER_HUB_LIST_TEAM_MEMBERS` | List Team Members | List members of a Docker Hub team (group) within an organization. Returns a paginated list of team members with their user details. Requires organization membership with appropriate permissions to view team members. |
| `DOCKER_HUB_LIST_TEAMS` | List Organization Teams | List all teams (groups) within a Docker Hub organization. Requires organization membership with appropriate permissions. Teams in Docker Hub are called 'groups' in the API. |
| `DOCKER_HUB_LIST_WEBHOOKS` | List Docker Hub repository webhooks | Lists all webhooks configured for a Docker Hub repository. Use this tool to retrieve webhook configurations for repositories you own or have admin access to. Webhooks are triggered when specific events occur in the repository (e.g., image push). Prerequisites: - You must have admin or write access to the repository - The repository must exist under the specified namespace Returns a paginated list of webhooks with their IDs, names, target URLs, configured events, and status. |
| `DOCKER_HUB_REMOVE_ORG_MEMBER` | Remove Organization Member | Remove a member from a Docker Hub organization. This action revokes the user's access to the organization and all its repositories. Requires organization admin privileges. The operation is idempotent - removing a non-member will not cause an error. |
| `DOCKER_HUB_REMOVE_TEAM_MEMBER` | Remove Team Member | Remove a user from a Docker Hub organization team (group). Use this action to revoke a user's membership from a specific team. The operation is idempotent - removing a user who is not a member will succeed silently. |

## Supported Triggers

None listed.

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

The Docker hub MCP server is an implementation of the Model Context Protocol that connects your AI agent to Docker hub. It provides structured and secure access so your agent can perform Docker hub 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 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 Docker hub account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Docker hub

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

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 Docker hub access
```bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id
```

### 4. Import modules

No description provided.
```python
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()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
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")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

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, docker hub)
- 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 Docker hub tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
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=["docker_hub"],
    )

    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 Docker hub actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Docker hub actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["docker_hub"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Docker hub actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
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}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

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 Docker hub
```python
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!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Docker hub, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
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=["docker_hub"],
    )

    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 Docker hub actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Docker hub 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!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["docker_hub"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Docker hub actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected Docker hub to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Docker hub 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 Docker hub MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/docker_hub/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/docker_hub/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/docker_hub/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/docker_hub/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/docker_hub/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/docker_hub/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/docker_hub/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/docker_hub/framework/cli)
- [Google ADK](https://composio.dev/toolkits/docker_hub/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/docker_hub/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/docker_hub/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/docker_hub/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/docker_hub/framework/crew-ai)

## Related Toolkits

- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.
- [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.
- [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.
- [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses.
- [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure.
- [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure.
- [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction.
- [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting.
- [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache.
- [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence.
- [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place.
- [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines.
- [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure.
- [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code.
- [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows.
- [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights.
- [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews.
- [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease.
- [Blocknative](https://composio.dev/toolkits/blocknative) - Blocknative delivers real-time mempool monitoring and transaction management for public blockchains. Instantly track pending transactions and optimize blockchain interactions with live data.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Docker hub MCP?

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

### Can I manage the permissions and scopes for Docker hub while using Tool Router?

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

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