SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Honeyhive MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Honeyhive MCP. Add new datapoints to your evaluation dataset, list all datasets in your honeyhive project, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Honeyhive logoHoneyhive
Api Key

Honeyhive is an AI observability and evaluation platform for analyzing LLM apps. It helps teams monitor, debug, and improve AI system reliability faster.

42 Tools

Introduction

This guide walks you through connecting Honeyhive to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Honeyhive agent that can create datasets and datapoints, log events and sessions, run and compare evaluations, define metrics, and manage configurations through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Honeyhive account through Composio's Honeyhive MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Honeyhive with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Honeyhive integration
  • Using Composio's Tool Router to dynamically load and access Honeyhive 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 Honeyhive MCP server, and what's possible with it?

The Honeyhive MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Honeyhive account. It provides structured and secure access to your AI observability platform, so your agent can perform actions like managing datasets, logging model and tool events, evaluating runs, and configuring project settings on your behalf.

  • Dataset management and organization: Create, retrieve, and delete datasets for your AI projects, helping you maintain organized and up-to-date evaluation data.
  • Efficient event logging: Log batches of model or external tool events, enabling comprehensive tracking and analysis of AI system interactions in real-time.
  • Data curation and cleanup: Add new datapoints to datasets or remove specific datapoints, ensuring your evaluation data remains accurate and relevant.
  • Streamlined evaluation workflows: Mark evaluation runs as completed and fetch project configuration details, making it easy to track progress and update run statuses automatically.

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

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

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.
3

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
4

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
5

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
6

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: ["honeyhive"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Honeyhive 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 Honeyhive-related tools through the MCP protocol
7

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 Honeyhive tools that the agent can use
8

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 honeyhive, 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
9

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 Honeyhive 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 Honeyhive 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: ["honeyhive"],
  });

  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 honeyhive, 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 Honeyhive 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.
TOOLS

Supported Tools

Every Honeyhive action and event your agent gets out of the box.

Add datapoints to dataset

Tool to add datapoints to a dataset.

Compare Experiment Runs

Tool to retrieve experiment comparison between two evaluation runs.

Compare Runs Events

Tool to compare events between two experiment runs side-by-side.

Batch Create Datapoints

Tool to create multiple datapoints in a single batch operation.

Create Batch Model Events

Tool to create multiple model events in a single request.

Create Batch Tool Events

Tool to log a batch of external API calls as tool events.

Create Configuration

Creates a new configuration in HoneyHive for managing LLM or pipeline settings.

Create Datapoint

Tool to create a new datapoint with input-output pairs.

Create Dataset

Tool to create a dataset.

Create Event

Tool to create a new event in HoneyHive to track execution of different parts of your application.

Create Metric

Tool to create a new metric in HoneyHive.

Create Model Event

Tool to create a new model event to log LLM call data.

Create Tool

Creates a new tool definition in a HoneyHive project.

Delete Datapoint

Delete a HoneyHive datapoint by its ID.

Delete Dataset

Delete a HoneyHive dataset by its ID.

End Evaluation Run

Tool to update an evaluation run's status and metadata.

Get Configurations

Tool to retrieve a list of configurations.

Get Datasets

Retrieve datasets from HoneyHive for a specified project.

Get Events

Tool to query events with filters and projections from HoneyHive.

Get Events By Session ID

Tool to retrieve the complete tree of nested events for a specific session.

Get Events Chart

Tool to retrieve charting and analytics data for events over time.

Get Metrics

Retrieves all metrics associated with a HoneyHive project.

Get Projects

Retrieve HoneyHive projects in the account, optionally filtering by a case-insensitive name substring.

Get Evaluation Run Details

Tool to get details of an evaluation run by its UUID.

Get Run Metrics

Tool to get event metrics for an experiment run.

Get Evaluation Runs

Tool to retrieve a list of evaluation runs from HoneyHive.

Get Runs Schema

Tool to retrieve the schema for experiment runs in HoneyHive.

Get Session

Retrieve a complete session tree by session ID from HoneyHive.

List Tools

List registered HoneyHive tools, optionally filtered by project and paginated.

Retrieve Datapoint

Retrieve a specific datapoint by its ID from HoneyHive.

Retrieve Datapoints

Retrieve datapoints from a HoneyHive project.

Retrieve Events

Retrieve and export events from a HoneyHive project.

Retrieve Experiment Result

Tool to retrieve the result of a specific experiment run.

Start Evaluation Run

Creates a new evaluation run to group and track multiple session events for analysis.

Start Session

Start a new HoneyHive session for tracing and observability.

Update Configuration

Tool to update an existing HoneyHive configuration.

Update Datapoint

Update an existing datapoint by ID.

Update Dataset

Tool to update an existing dataset.

Update Event

Update an existing HoneyHive event by ID.

Update Metric

Tool to update an existing metric.

Update Project

Updates an existing HoneyHive project's name or description.

Update Tool

Tool to update an existing tool in HoneyHive.

FRAMEWORKS

How to build Honeyhive MCP Agent with another framework

Claude Code logo

Claude Code

Use Honeyhive MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Honeyhive MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Honeyhive MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Honeyhive MCP with Claude Agent SDK

Codex logo

Codex

Use Honeyhive MCP with Codex

OpenClaw logo

OpenClaw

Use Honeyhive MCP with OpenClaw

Hermes logo

Hermes

Use Honeyhive MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Honeyhive MCP with Atomic Agent

Google ADK logo

Google ADK

Use Honeyhive MCP with Google ADK

LangChain logo

LangChain

Use Honeyhive MCP with LangChain

Mastra AI logo

Mastra AI

Use Honeyhive MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Honeyhive MCP with LlamaIndex

CrewAI logo

CrewAI

Use Honeyhive MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Honeyhive MCP with Pydantic AI

AutoGen logo

AutoGen

Use Honeyhive MCP with AutoGen

FAQ

Frequently asked questions

Start with Honeyhive.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Honeyhive tool your agent needs.Free to start.

Start building