How to integrate Hookdeck MCP with LlamaIndex

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

Introduction

This guide walks you through connecting Hookdeck to LlamaIndex using the Composio tool router. By the end, you'll have a working Hookdeck agent that can retry all failed webhook events from today, create a new source for github webhooks, bookmark this event for quick review later, cancel scheduled retries for a specific webhook through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Hookdeck account through Composio's Hookdeck 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 Hookdeck
  • Connect LlamaIndex to the Hookdeck MCP server
  • Build a Hookdeck-powered agent using LlamaIndex
  • Interact with Hookdeck 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 Hookdeck MCP server, and what's possible with it?

The Hookdeck MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Hookdeck account. It provides structured and secure access to your webhook management platform, so your agent can perform actions like routing webhooks, managing events, configuring sources and destinations, and automating retries or cancellations on your behalf.

  • Automated event management: Let your agent bulk cancel or retry multiple webhook events, keeping your pipeline clean and efficient without manual intervention.
  • Source and destination setup: Have the agent create, configure, and manage Hookdeck sources and destinations for seamless webhook routing between services.
  • Connection orchestration: Direct your agent to establish new connections between sources and destinations, ensuring events flow exactly where you want them to go.
  • Payload transformation: Empower the agent to create custom payload transformations using JavaScript, modifying webhook data before it reaches your endpoints.
  • Bookmarking and cleanup: Ask your agent to bookmark important events for quick access or delete outdated bookmarks to keep your workspace organized.

Supported Tools & Triggers

Tools
Bulk Cancel Hookdeck EventsTool to create a bulk cancellation job for events.
Bulk Retry Hookdeck EventsTool to initiate a bulk retry for a set of events.
Cancel Hookdeck EventTool to cancel all future delivery attempts for a specific event.
Cancel Hookdeck Scheduled RetriesTool to cancel all future scheduled retries for an event.
Create Hookdeck BookmarkTool to create a new bookmark.
Create Hookdeck ConnectionTool to create a connection between a source and a destination.
Create Hookdeck DestinationTool to create a new Hookdeck destination.
Create Hookdeck SourceTool to create a new Hookdeck source.
Create Hookdeck TransformationTool to create a new Hookdeck transformation.
Delete Hookdeck BookmarkTool to delete a specific bookmark by its ID.
Delete Hookdeck ConnectionTool to delete a specific connection by its ID.
Delete Hookdeck DestinationTool to delete a specific destination by its ID.
Delete Hookdeck SourceTool to delete a specific source by its ID.
Delete Hookdeck TransformationTool to delete a specific transformation by its ID.
Get Hookdeck AttemptTool to retrieve details of a specific Hookdeck attempt by its ID.
Get attemptsTool to list delivery attempts for your Hookdeck account.
Get Hookdeck ConnectionTool to retrieve details of a specific Hookdeck connection.
Hookdeck: Get ConnectionsTool to list Hookdeck connections.
Get Hookdeck DestinationTool to retrieve details of a specific Hookdeck destination.
Hookdeck: Get DestinationsTool to list Hookdeck destinations.
Get eventsTool to list events for your Hookdeck account.
Get Hookdeck RequestTool to retrieve details of a specific Hookdeck request.
Hookdeck: Get RequestsTool to list Hookdeck requests.
Get sourcesTool to retrieve all sources associated with your Hookdeck account.
Get Hookdeck TransformationTool to retrieve details of a specific Hookdeck transformation.
Get transformationsTool to list Hookdeck transformations.
Get Hookdeck SourceTool to retrieve details of a specific Hookdeck source.
Send Hookdeck Source RequestTool to send HTTP requests to a Hookdeck Source URL.
List Hookdeck BookmarksTool to list bookmarks.
Hookdeck: List IssuesTool to list all issues detected in your Hookdeck account.
Manually Retry Hookdeck EventTool to manually retry a specific Hookdeck event delivery.
Replay Hookdeck EventTool to replay a specific Hookdeck event.
Resolve Hookdeck IssueTool to resolve a Hookdeck issue.
Retrieve Hookdeck IssueTool to retrieve details of a specific Hookdeck issue.
Trigger Hookdeck BookmarkTool to trigger a stored request via its bookmark ID.
Hookdeck Update ConnectionTool to update an existing connection.
Update Hookdeck DestinationTool to update an existing Hookdeck destination.
Hookdeck Update SourceTool to update a Hookdeck source.
Update Hookdeck TransformationTool to update an existing Hookdeck transformation.

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 Hookdeck account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Hookdeck

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 Hookdeck 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 hookdeck_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=["hookdeck"],
    )

    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 Hookdeck actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Hookdeck 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, hookdeck)
  • 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 Hookdeck 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 Hookdeck 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 Hookdeck

Run the agent

npx ts-node llamaindex-agent.ts

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

Complete Code

Here's the complete code to get you started with Hookdeck 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=["hookdeck"],
    )

    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 Hookdeck actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Hookdeck 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 Hookdeck to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Hookdeck 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 Hookdeck MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Hookdeck MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Hookdeck MCP with Claude Agent SDK

Google ADK

Google ADK

Use Hookdeck MCP with Google ADK

LangChain

LangChain

Use Hookdeck MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Hookdeck MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Hookdeck MCP with Mastra AI

CrewAI

CrewAI

Use Hookdeck MCP with CrewAI

FAQ

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

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

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

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

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
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