How to integrate Hookdeck MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Hookdeck logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Hookdeck to Vercel AI SDK v6 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 through natural language commands.

This guide will help you understand how to give your Vercel AI SDK 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.

Also integrate Hookdeck with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Hookdeck integration
  • Using Composio's Tool Router to dynamically load and access Hookdeck tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

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
Add Custom DomainTool to add a custom domain to the Hookdeck project.
Bulk Cancel Hookdeck EventsTool to create a bulk cancellation job for events.
Bulk Retry Hookdeck EventsInitiate a bulk retry for multiple events matching the specified filters.
Cancel Hookdeck EventCancel all future delivery attempts for a Hookdeck event.
Cancel Event Bulk RetryTool to cancel an ongoing events bulk retry operation.
Cancel Request Bulk RetryTool to cancel an in-progress requests bulk retry operation.
Cancel Hookdeck Scheduled RetriesTool to cancel all future scheduled retries for an event.
Count Hookdeck ConnectionsTool to count Hookdeck connections with optional filters.
Count Hookdeck DestinationsTool to count Hookdeck destinations with optional filters.
Count Hookdeck SourcesTool to count Hookdeck sources with optional filters.
Create Hookdeck BookmarkTool to create a bookmark for a specific event request in Hookdeck.
Create Hookdeck ConnectionTool to create a connection between a source and a destination.
Create Hookdeck DestinationTool to create a new Hookdeck destination.
Create Ignored Event Bulk RetryTool to create an ignored events bulk retry operation.
Create Hookdeck IntegrationTool to create a new Hookdeck integration.
Create Hookdeck Issue TriggerTool to create an issue trigger in Hookdeck.
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 DestinationPermanently deletes a Hookdeck destination by its ID.
Delete Hookdeck IntegrationTool to delete a specific integration by its ID.
Delete Hookdeck Issue TriggerTool to delete a specific issue trigger by its ID.
Delete Hookdeck SourceTool to delete a specific source by its ID.
Delete Hookdeck TransformationPermanently delete a Hookdeck transformation by its ID.
Disable Hookdeck ConnectionTool to disable a connection by its ID.
Disable Hookdeck DestinationTool to disable a Hookdeck destination.
Disable Hookdeck Issue TriggerTool to disable a Hookdeck issue trigger.
Disable Hookdeck SourceTool to disable a Hookdeck source.
Enable Hookdeck ConnectionTool to enable a disabled Hookdeck connection.
Enable Hookdeck DestinationEnable a previously disabled Hookdeck destination by its ID.
Enable Hookdeck Issue TriggerTool to enable a Hookdeck issue trigger.
Enable Hookdeck SourceTool to enable a disabled Hookdeck source.
Generate Event Bulk Cancel PlanTool to generate a preview plan for bulk event cancellation.
Generate Event Bulk Retry PlanTool to generate an events bulk retry plan.
Generate Ignored Event Bulk Retry PlanGenerate an ignored events bulk retry plan to estimate the scope before execution.
Generate Request Bulk Retry PlanTool to generate a requests bulk retry plan.
Get Hookdeck AttemptTool to retrieve a specific Hookdeck delivery attempt by ID.
Get attemptsLists delivery attempts for your Hookdeck account.
Get attempts metricsTool to query aggregated attempt metrics with time-based grouping and filtering.
Get Hookdeck BookmarkTool to retrieve a single bookmark by its ID.
Get Bookmark Raw BodyTool to retrieve the raw body data of a bookmarked request.
Get Hookdeck ConnectionRetrieves details of a specific Hookdeck connection by its ID.
Hookdeck: Get ConnectionsTool to list Hookdeck connections.
Get Hookdeck DestinationRetrieve details of a specific Hookdeck destination by ID.
Hookdeck: Get DestinationsTool to list Hookdeck destinations.
Get EventTool to retrieve a specific Hookdeck event by ID.
Get Event Bulk Cancel StatusTool to retrieve the status of a bulk event cancellation operation.
Get Event Bulk CancelsTool to list event bulk cancel operations for your Hookdeck account.
Get Event Bulk RetriesTool to retrieve bulk retry operations for Hookdeck events.
Get Event Bulk Retry StatusTool to retrieve the status of a bulk event retry operation.
Get Event Raw BodyTool to retrieve the raw body data of an event.
Get eventsTool to list events for your Hookdeck account.
Get events by issue metricsTool to query event metrics grouped by individual issue IDs.
Get Events MetricsTool to query aggregated event metrics with time-based grouping and filtering.
Get events pending timeseries metricsTool to query aggregated events pending timeseries metrics with time-based grouping and filtering.
Get Ignored Event Bulk RetriesTool to retrieve ignored events bulk retry operations for Hookdeck.
Get Ignored Event Bulk Retry StatusTool to retrieve the status of an ignored events bulk retry operation.
Get Hookdeck IntegrationTool to retrieve details of a specific Hookdeck integration.
Get Hookdeck IntegrationsTool to retrieve a list of Hookdeck integrations.
Get Hookdeck Issue CountTool to get the count of Hookdeck issues with optional filters.
Get Hookdeck Issue TriggerTool to retrieve a single Hookdeck issue trigger by its ID.
Get issue triggersTool to list issue triggers for your Hookdeck account.
Get Queue Depth MetricsTool to query queue depth metrics for destinations (pending events count and age).
Get Hookdeck RequestRetrieve detailed information about a specific Hookdeck request by ID.
Get Request Bulk RetriesTool to retrieve bulk retry operations for Hookdeck requests.
Get Request Bulk Retry StatusTool to retrieve the status of a requests bulk retry operation.
Get Request EventsTool to retrieve events associated with a specific Hookdeck request.
Get Request Ignored EventsRetrieve the list of ignored events for a specific Hookdeck request.
Get Request Raw BodyTool to retrieve the raw body data of a request.
Hookdeck: Get RequestsTool to list Hookdeck requests.
Get requests metricsTool to query aggregated request metrics with time-based grouping and filtering.
Get Hookdeck SourceTool to retrieve details of a specific Hookdeck source.
Get sourcesTool to retrieve all sources associated with your Hookdeck account.
Get Hookdeck TransformationRetrieves the complete details of a specific Hookdeck transformation by its ID.
Get Transformation ExecutionRetrieve a specific transformation execution by transformation ID and execution ID.
Get transformation executionsTool to retrieve executions for a specific Hookdeck transformation.
Get transformationsTool to list Hookdeck transformations.
Get Transformations CountTool to get the count of Hookdeck transformations with optional filters.
Get transformations metricsTool to query aggregated transformation execution metrics with time-based grouping and filtering.
List Hookdeck BookmarksTool to list bookmarks.
List Custom DomainsTool to list all custom domains and their verification statuses for the Hookdeck project.
Hookdeck: List IssuesTool to list all issues detected in your Hookdeck account.
Hookdeck Pause ConnectionTool to pause a Hookdeck connection.
Publish Event to HookdeckTool to publish a webhook event to Hookdeck using the Publish API.
Replay Hookdeck EventReplay (retry) a specific Hookdeck event delivery.
Resolve Hookdeck IssueTool to resolve a Hookdeck issue.
Retrieve Hookdeck IssueRetrieves detailed information about a specific Hookdeck issue by its ID.
Send Hookdeck Source RequestTool to send HTTP requests to a Hookdeck Source URL.
Test Hookdeck TransformationTool to test a Hookdeck transformation code before deploying it.
Toggle Webhook NotificationsTool to toggle webhook notifications for the project.
Trigger Hookdeck BookmarkTrigger a Hookdeck bookmark to replay its stored webhook request.
Unpause Hookdeck ConnectionTool to unpause a paused Hookdeck connection.
Update Hookdeck BookmarkTool to update an existing bookmark in Hookdeck.
Hookdeck Update ConnectionUpsert (create or update) a Hookdeck connection between a source and destination.
Update Connection by IDTool to update an existing Hookdeck connection by its ID.
Update Hookdeck DestinationTool to update an existing Hookdeck destination.
Update Hookdeck IntegrationTool to update an existing Hookdeck integration.
Update Hookdeck Issue TriggerTool to update an issue trigger in Hookdeck.
Update Hookdeck SourceUpdate an existing Hookdeck source's name, type, or description.
Update Hookdeck TransformationTool to update an existing Hookdeck transformation.
Upsert Hookdeck DestinationTool to create or update a Hookdeck destination.
Upsert Hookdeck Issue TriggerTool to create or update an issue trigger in Hookdeck using upsert semantics.
Upsert Hookdeck SourceTool to create or update a Hookdeck source by name.
Upsert Hookdeck TransformationTool to create or update a Hookdeck transformation by name.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["hookdeck"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Hookdeck tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Hookdeck-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Hookdeck tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to hookdeck, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

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

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Hookdeck tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Hookdeck and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["hookdeck"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to hookdeck, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

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

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Hookdeck agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Hookdeck MCP Agent with another framework

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 Vercel AI SDK v6?

Yes, you can. Vercel AI SDK v6 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.