How to integrate Elevenreader MCP with Vercel AI SDK v6

GET STARTED FOR FREE
Framework Integration Gradient
Elevenreader Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting Elevenreader to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Elevenreader agent that can convert a blog post to audio narration, summarize this article and read aloud, generate an audio version of meeting notes through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Elevenreader account through Composio's Elevenreader 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:
  • How to set up and configure a Vercel AI SDK agent with Elevenreader integration
  • Using Composio's Tool Router to dynamically load and access Elevenreader 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 Elevenreader MCP server, and what's possible with it?

The Elevenreader MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Elevenreader account. It provides structured and secure access so your agent can perform Elevenreader operations on your behalf.

Supported Tools & Triggers

Tools
Add Documentation To Knowledge BaseTool to add documentation to a conversational AI agent's knowledge base.
Add Pronunciation Dictionary From FileTool to add a pronunciation dictionary from a .
Add Pronunciation Dictionary From RulesTool to add a pronunciation dictionary from rules in ElevenLabs.
Add Pronunciation Dictionary RulesTool to add pronunciation rules to an ElevenLabs pronunciation dictionary.
Add Shared VoiceTool to add a shared voice from another user's public library to your own voice library.
Add ToolTool to add a conversational AI tool to ElevenLabs ConvAI.
Calculate Public LLM Expected CostTool to calculate expected LLM usage costs based on prompt length, knowledge base size, and RAG configuration.
Cancel batch callTool to cancel an active batch call operation.
Compute RAG IndexTool to compute RAG index for a knowledge base document.
Create AgentTool to create a conversational AI agent with ElevenLabs.
Create Agent Response TestTool to create an agent response test for testing conversational AI agents.
Create Audio Native ProjectTool to create an Audio Native enabled project on ElevenLabs.
Create Batch CallTool to submit a batch call request to ElevenLabs ConvAI.
Create File DocumentTool to create a file document in the ElevenLabs knowledge base.
Create FolderTool to create a folder in the ElevenLabs knowledge base.
Create Convai Workspace SecretTool to create a Convai workspace secret in ElevenLabs.
Create Text DocumentTool to create a text document in the ElevenLabs knowledge base.
Create URL DocumentTool to create a URL document in the ElevenLabs knowledge base.
Delete AgentTool to permanently delete an agent from ElevenLabs.
Delete Batch CallTool to delete a specific batch call.
Delete Agent Response TestTool to delete an agent response test.
Delete ConversationTool to delete a conversation by its unique ID.
Delete DubbingTool to permanently delete a dubbing project by its ID.
Delete Knowledge Base DocumentTool to permanently delete a document from the knowledge base.
Delete Phone NumberTool to permanently delete a phone number from ElevenLabs ConvAI.
Delete RAG IndexTool to permanently delete a RAG index from a knowledge base document.
Delete Convai Workspace SecretTool to delete a specific Convai workspace secret.
Delete Speech History ItemTool to permanently delete a speech history item by its ID.
Delete ToolTool to permanently delete a conversational AI tool from ElevenLabs.
Delete Transcript By IdTool to permanently delete a speech-to-text transcript by its ID.
Download Speech History ItemsTool to download speech history items from ElevenLabs.
Duplicate AgentTool to duplicate an existing agent.
Edit VoiceTool to edit an existing voice in ElevenLabs.
Edit Voice SettingsTool to edit voice settings for a specific voice in ElevenLabs.
Generate Composition PlanTool to generate a music composition plan using ElevenLabs Music API.
Get agentTool to retrieve complete details for a specific conversational AI agent by ID.
Get Agent Knowledge Base SizeTool to retrieve the size of a conversational AI agent's knowledge base.
Get Agent Shareable LinkTool to get a shareable link for a conversational AI agent.
Calculate Agent LLM Expected CostTool to calculate expected LLM usage costs for a conversational AI agent.
Get Agent Response TestTool to retrieve agent response test details by test ID.
Get Agent Response Tests SummariesTool to retrieve agent response test summaries by test IDs.
Get Agent SummariesTool to retrieve summaries for multiple agents by their IDs.
Get Agent Widget ConfigTool to retrieve the widget configuration for a conversational AI agent.
Get Audio From History ItemTool to retrieve the audio file from a speech history item.
Get Audio Native Project SettingsTool to retrieve audio native project settings from ElevenLabs.
Get Batch Call By IdTool to retrieve a batch call by its ID.
Get conversation historyTool to retrieve complete conversation details including transcript, metadata, and analysis.
Get ConversationsTool to retrieve conversations from ElevenLabs Conversational AI.
Get Conversation Signed LinkTool to get a signed URL for a conversation with an agent.
Get ConvAI dashboard settingsTool to retrieve ConvAI dashboard settings including configured charts.
Get Documentation From Knowledge BaseTool to retrieve a specific document from a conversational AI agent's knowledge base by document ID.
Get Dubbed FileTool to download a dubbed audio or video file from a dubbing project.
Get Dubbing MetadataTool to retrieve metadata for a dubbing project by ID.
Get Dubbed TranscriptTool to retrieve the transcript of a dubbed audio or video file.
Get Dubbing TranscriptsTool to retrieve transcripts from a dubbing project in various formats.
Get Generate Voice ParametersTool to retrieve voice generation parameters from ElevenLabs.
Get Knowledge Base ContentTool to retrieve the text content of a knowledge base document by ID.
Get Knowledge Base Dependent AgentsTool to retrieve the list of conversational AI agents that depend on a specific knowledge base document.
Get Knowledge Base Source File URLTool to retrieve a signed URL for downloading the source file of a document from the knowledge base.
Get Knowledge Base SummariesTool to retrieve summaries for multiple knowledge base documents by their IDs.
Get Library VoicesTool to retrieve shared voices from the ElevenLabs voice library.
Get Live CountTool to retrieve the count of active ongoing conversations.
Get ModelsTool to retrieve available ElevenLabs speech synthesis models.
Get Or Create RAG IndexesTool to compute or retrieve RAG indexes for knowledge base documents in batch.
Get phone numberTool to retrieve details for a specific phone number by ID.
Get Pronunciation DictionariesTool to get a list of pronunciation dictionaries and their metadata.
Get Pronunciation Dictionary MetadataTool to retrieve metadata for a specific pronunciation dictionary by ID.
Get Pronunciation Dictionary Version PLSTool to download a PLS file with pronunciation dictionary version rules.
Get RAG IndexesTool to retrieve RAG indexes for a specific knowledge base document.
Get RAG Index OverviewTool to retrieve an overview of the RAG (Retrieval-Augmented Generation) index.
Get Resource MetadataTool to retrieve metadata and sharing permissions for a workspace resource.
Get ConvAI workspace secretsTool to retrieve ConvAI workspace secrets with pagination support.
Get ConvAI workspace settingsTool to retrieve ConvAI workspace settings including MCP server access, LiveKit stack configuration, RAG retention, and webhook settings.
Get Signed URL (Deprecated)Tool to get a signed URL for an agent conversation.
Get Similar Library VoicesTool to find similar voices from the ElevenLabs library by uploading an audio sample.
Get Single Use TokenTool to create a single-use token for ElevenLabs API.
Get Speech HistoryTool to list generated speech history items from ElevenLabs.
Get speech history item by IDTool to retrieve complete details for a specific speech history item by ID.
Get Test InvocationTool to retrieve test invocation details by invocation ID.
Get toolTool to retrieve complete details for a specific conversational AI tool by ID.
Get Tool Dependent AgentsTool to retrieve the list of conversational AI agents that depend on a specific tool.
Get ConvAI ToolsTool to retrieve ConvAI tools with pagination support.
Get Transcript By IDTool to retrieve a speech-to-text transcript by its unique ID.
Get Characters Usage MetricsTool to retrieve character usage metrics from ElevenLabs.
Get User InfoTool to retrieve information about the authenticated user, including subscription details, character limits, and voice quotas.
Get User Subscription InfoTool to retrieve detailed subscription information for the authenticated user.
Get User Voices V2Tool to retrieve voices using the V2 API from ElevenLabs.
Get Voice by IDTool to retrieve complete details for a specific voice by ID.
Get Voice SettingsTool to retrieve the current settings for a specific voice.
Get Default Voice SettingsTool to retrieve default voice settings for speech synthesis.
Get Workspace Batch CallsTool to get all batch calls for a workspace.
Get Workspace Service AccountsTool to retrieve all service accounts in the workspace.
Handle SIP Trunk Outbound CallTool to initiate an outbound call via SIP trunk using ElevenLabs ConvAI.
Import Phone NumberTool to import a phone number (Twilio or SIP trunk) into ElevenLabs ConvAI.
Isolate Audio StreamTool to isolate vocals/speech from audio files using ElevenLabs Audio Isolation API.
List Agent BranchesTool to list all branches for a specific agent.
List Agent Response TestsTool to list agent response tests from ElevenLabs conversational AI.
List AgentsTool to list conversational AI agents from ElevenLabs.
List DubsTool to list dubbing projects from ElevenLabs.
List Knowledge BasesTool to list knowledge base documents from ElevenLabs.
List MCP ServersTool to list all MCP (Model Context Protocol) server configurations in the workspace.
List Phone NumbersTool to list all phone numbers available in your ElevenLabs ConvAI workspace.
List Test InvocationsTool to list test invocations for a specific conversational AI agent.
List WhatsApp AccountsTool to list all WhatsApp accounts available in your ElevenLabs ConvAI workspace.
List Workspace WebhooksTool to list all webhooks configured in your ElevenLabs workspace.
Bulk Move Knowledge Base EntitiesTool to bulk move documents or folders to a target folder in the knowledge base.
Move Knowledge Base EntityTool to move a document or folder to a target folder in the knowledge base.
Patch Agent SettingsTool to patch (partially update) an agent's settings.
Update Pronunciation DictionaryTool to update a pronunciation dictionary.
Post Agent AvatarTool to upload an avatar image for a conversational AI agent.
Register Twilio CallTool to register a Twilio call with ElevenLabs ConvAI and return TwiML.
Remove Pronunciation Dictionary RulesTool to remove rules from a pronunciation dictionary.
Resubmit TestsTool to resubmit failed or specific tests from a previous test invocation.
Retry batch callTool to retry a failed or cancelled batch call.
Run Agent Test SuiteTool to run tests on a conversational AI agent.
Run Conversation SimulationTool to simulate a conversation between an agent and an AI user.
Simulate Conversation (Stream)Tool to simulate a conversation with an AI agent using a streaming endpoint.
Update Agent Response TestTool to update an existing agent response test in ElevenLabs ConvAI.
Update Audio Native Project ContentTool to update audio-native project content by uploading a new txt or HTML file.
Update ConvAI SettingsTool to update ConvAI workspace settings in ElevenLabs.
Update ConvAI dashboard settingsTool to update ConvAI dashboard settings including chart configurations.
Update DocumentTool to update a document in the ElevenLabs knowledge base.
Update Phone NumberTool to update a phone number's configuration in ElevenLabs ConvAI.
Update Convai Workspace SecretTool to update a Convai workspace secret by ID.
Update ToolTool to update a conversational AI tool configuration.

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:
  • 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: ["elevenreader"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Elevenreader 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 Elevenreader-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 Elevenreader 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 elevenreader, 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("\nđź‘‹ 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 Elevenreader 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 Elevenreader 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: ["elevenreader"],
  });

  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 elevenreader, 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("\nđź‘‹ Session ended.");
    process.exit(0);
  });
}

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

Conclusion

You've successfully built a Elevenreader 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 Elevenreader MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Elevenreader MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Elevenreader MCP with Claude Agent SDK

Google ADK

Google ADK

Use Elevenreader MCP with Google ADK

LangChain

LangChain

Use Elevenreader MCP with LangChain

Mastra AI

Mastra AI

Use Elevenreader MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Elevenreader MCP with LlamaIndex

CrewAI

CrewAI

Use Elevenreader MCP with CrewAI

Claude Code

Claude Code

Use Elevenreader MCP with Claude Code

Codex

Codex

Use Elevenreader MCP with Codex

FAQ

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

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

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

Yes, absolutely. You can configure which Elevenreader 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 Elevenreader 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