SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Parseur MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Parseur MCP. List all documents in your invoices mailbox, create a webhook to send parsed receipts, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Parseur logoParseur
Api Key

Parseur is an AI-powered data extraction platform that parses emails, PDFs, and documents into structured data. Automate tedious data entry and get actionable information, fast.

26 Tools

Introduction

This guide walks you through connecting Parseur to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Parseur agent that can create and manage mailboxes, upload email documents for parsing, fetch parsed results, reprocess documents, and configure webhooks through natural language commands.

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

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

Also integrate Parseur 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 Parseur integration
  • Using Composio's Tool Router to dynamically load and access Parseur 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 Parseur MCP server, and what's possible with it?

The Parseur MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Parseur account. It provides structured and secure access to your Parseur data extraction workflows, so your agent can perform actions like managing mailboxes, handling documents, configuring webhooks, and automating template operations on your behalf.

  • Mailbox management and discovery: Let your agent list, browse, and filter all Parseur mailboxes to keep tabs on your parsing operations and document streams.
  • Document listing and retrieval: Effortlessly fetch documents from specific mailboxes, enabling automated sorting, searching, or pagination of your parsed files.
  • Template and parsing rule automation: Ask your agent to list templates within any mailbox, so you can quickly inspect or update parsing rules as your data extraction needs evolve.
  • Webhook configuration and control: Enable your agent to create, update, pause, enable, or delete webhooks, making it easy to automate real-time data delivery to your other systems.
  • Comprehensive webhook inspection: Retrieve detailed webhook information or list all webhooks for a mailbox, ensuring you always know how and where your parsed data is flowing.

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: ["parseur"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Parseur 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 Parseur-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 Parseur 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 parseur, 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 Parseur 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 Parseur 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: ["parseur"],
  });

  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 parseur, 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 Parseur 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 Parseur action and event your agent gets out of the box.

Copy Document

Tool to copy a document to another mailbox.

Copy Mailbox

Tool to copy a mailbox (parser) in Parseur.

Create custom download

Tool to create a custom download (export configuration) for a mailbox.

Create mailbox

Tool to create a new mailbox (parser) in Parseur.

Delete custom download

Tool to delete a custom download (export configuration) from a mailbox.

Delete document

Tool to delete a specific document by ID.

Delete mailbox

Tool to delete a mailbox (parser) by ID.

Delete webhook

Tool to delete a specific webhook.

Disable webhook

Tool to disable a webhook for a mailbox.

Enable webhook

Enables a paused webhook for a specified mailbox, allowing it to receive and forward parsed document events.

Get Bootstrap Config

Tool to retrieve bootstrap configuration data.

Get Document

Tool to retrieve full details of a specific document by ID.

Get Document Logs

Tool to get document logs for a specific document.

Get Mailbox by ID

Tool to retrieve full mailbox (parser) configuration by ID.

Get Mailbox Schema

Tool to retrieve the JSON schema for a mailbox's parsed fields.

List Custom Downloads

Retrieve custom downloads (export configurations) and their download URLs for a mailbox.

List Documents in Mailbox

Tool to list documents within a specific mailbox.

List Mailboxes (Full Details)

List mailboxes with pagination, document counts, processing statistics, and configuration details such as field settings, processing options, and webhooks.

List Templates for Mailbox

Tool to list all templates in a given mailbox.

Reprocess a document

Tool to reprocess a document.

Retrieve a webhook

Tool to retrieve details of a specific webhook.

Skip a document

Tool to skip a document.

Update custom download

Update a mailbox's custom download configuration, including its name, field list, or export type.

Update Mailbox

Tool to update a mailbox (parser) configuration.

Update webhook

Tool to update an existing webhook’s settings.

Upload Email Document

Tool to upload an email or text document to Parseur for parsing.

FRAMEWORKS

How to build Parseur MCP Agent with another framework

Claude Code logo

Claude Code

Use Parseur MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Parseur MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Parseur MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Parseur MCP with Claude Agent SDK

Codex logo

Codex

Use Parseur MCP with Codex

OpenClaw logo

OpenClaw

Use Parseur MCP with OpenClaw

Hermes logo

Hermes

Use Parseur MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Parseur MCP with Atomic Agent

Google ADK logo

Google ADK

Use Parseur MCP with Google ADK

LangChain logo

LangChain

Use Parseur MCP with LangChain

Mastra AI logo

Mastra AI

Use Parseur MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Parseur MCP with LlamaIndex

CrewAI logo

CrewAI

Use Parseur MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Parseur MCP with Pydantic AI

AutoGen logo

AutoGen

Use Parseur MCP with AutoGen

FAQ

Frequently asked questions

With a standalone Parseur MCP server, the agents and LLMs can only access a fixed set of Parseur tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Parseur and many other apps based on the task at hand, all through a single MCP endpoint.

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 Parseur tools.

Yes, absolutely. You can configure which Parseur 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.

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 Parseur data and credentials are handled as safely as possible.

Start with Parseur.It takes 30 seconds.

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

Start building