Documenso with Vercel AI SDK

How to integrate Documenso MCP with Vercel AI SDK v6

Trusted by

GET STARTED FOR FREE GET A DEMO

30 min · no commitment · see it on your stack

Introduction Also integrate Documenso with TL;DR What is Vercel AI SDK What is the Documenso MCP server Supported Tools & Triggers Creating MCP Server - Stand-alone vs Composio SDK Step-by-step Guide Complete Code Conclusion How to build Documenso MCP Agent with another framework Explore Other Toolkits FAQ

Connect Documenso without Auth hassles

We manage OAuth, API Key, token refresh, and scopes, you just build.

Try for Free

Introduction

This guide walks you through connecting Documenso to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Documenso agent that can send a contract to client for signature, download the latest signed nda document, list all templates for onboarding paperwork through natural language commands.

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

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

Also integrate Documenso with

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenClaw Hermes CLI Google ADK LangChain Mastra AI LlamaIndex CrewAI

TL;DR

Here's what you'll learn:

How to set up and configure a Vercel AI SDK agent with Documenso integration
Using Composio's Tool Router to dynamically load and access Documenso 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 Documenso MCP server, and what's possible with it?

The Documenso MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Documenso account. It provides structured and secure access to your electronic signature workflows, so your agent can create documents, distribute them for signing, manage templates, and download signed files automatically on your behalf.

Automated document creation and duplication: Prompt your agent to generate new documents or make exact copies of existing ones for rapid workflow setup.
Seamless document distribution for signatures: Let your agent send documents to one or more recipients, kicking off secure e-signature flows without manual intervention.
Template management and retrieval: Ask your agent to list, fetch, or delete document templates, keeping your signing processes organized and up-to-date.
Download and access signed documents: Have your agent retrieve finalized, signed PDFs automatically for seamless archiving or sharing.
Streamlined document organization: Direct your agent to move documents between personal and team spaces, or remove unnecessary fields to keep everything tidy and current.

Supported Tools & Triggers

Tools

Create Document BetaTool to create a new document using the beta endpoint that returns a presigned URL for file upload.

Create Document FieldTool to create a single field for a document.

Create Document Fields (Bulk)Tool to create multiple fields on a document in a single operation.

Create Document RecipientTool to create a single recipient for a document.

Create Document Recipients BulkTool to create multiple recipients for a document at once.

Create Embedding Presign Token V2 BetaCreate a presign token for Documenso embedded authoring sessions.

Create EnvelopeTool to create a new envelope in Documenso.

Create Envelope AttachmentCreate a new attachment for an envelope in Documenso.

Create Envelope Items BulkTool to create multiple items for an envelope with optional file attachments.

Create Envelope Recipients BulkTool to create multiple recipients for an envelope in bulk.

Create FolderCreate a new folder in Documenso to organize documents or templates.

Create Template BetaTool to create a new template using the beta endpoint that returns a presigned URL for file upload.

Create Template FieldTool to create a single field for a template.

Create Template Fields (Bulk)Tool to create multiple fields on a template in a single operation.

Create Template RecipientTool to create a single recipient for a template.

Create Template Recipients BulkTool to create multiple recipients for a template at once.

Delete DocumentTool to delete a document.

Delete Document AttachmentTool to delete an attachment from a document.

Delete Document FieldTool to delete a single document field by ID.

Delete Document FieldsTool to delete one or more fields from a document.

Delete Document RecipientTool to delete a recipient from a document.

Delete EnvelopeTool to permanently delete an envelope.

Delete Envelope AttachmentTool to delete an attachment from an envelope.

Delete Envelope FieldTool to delete a field from an envelope.

Delete Envelope ItemTool to delete an item from an envelope.

Delete Envelope RecipientTool to delete a recipient from an envelope.

Delete FolderTool to permanently delete a folder.

Delete TemplatePermanently delete a template by its ID.

Delete Template Direct LinkDelete a direct link for a template.

Delete Template RecipientTool to delete a recipient from a template.

Delete Template V2Tool to permanently delete a template using the v2 API.

Distribute Document V2Tool to distribute a document for signing.

Distribute EnvelopeTool to distribute an envelope to recipients for signing.

Download Envelope ItemDownload an envelope item as PDF.

Download Signed DocumentDownload a completed/signed document as PDF.

Duplicate Document V2Tool to duplicate a document.

Duplicate Envelope V2Tool to duplicate an envelope with all its settings.

Duplicate TemplateTool to duplicate a template with all its settings.

Find DocumentsFind documents based on search criteria with filtering and pagination.

Find Documents V2Retrieve a paginated list of documents with optional filtering and sorting.

Find EnvelopesTool to find envelopes based on search criteria, filters, and pagination.

Find FoldersTool to find folders based on search criteria and filters.

Find TemplatesRetrieve a paginated list of templates with optional filtering and search.

Get Document By IDRetrieve complete information about a document by its ID.

Get Document FieldTool to retrieve a document field by its ID.

Get Document RecipientTool to retrieve detailed information about a document recipient by their ID.

Get Documents By IDsRetrieve multiple documents by their IDs in a single request.

Get Envelope AttachmentTool to find all attachments for a specific envelope.

Get Envelope Audit LogTool to retrieve audit logs for an envelope.

Get Envelope By IDRetrieve complete information about an envelope by its ID.

Get Envelope FieldTool to fetch an envelope field by ID.

Get Envelope RecipientTool to retrieve detailed information about an envelope recipient by their ID.

Get Envelopes By IDsTool to retrieve multiple envelopes by their IDs.

Get Template By IDRetrieve complete information about a template by its ID.

Get Template FieldTool to fetch a template field by ID.

Get Template RecipientTool to retrieve detailed information about a template recipient by their ID.

Get Templates By IDsRetrieve multiple templates by their IDs in a single request.

List TemplatesTool to list templates.

Move Document V2Tool to move a document to a team.

Redistribute Document V2Re-send signing request emails to specified recipients of a document.

Redistribute EnvelopeTool to redistribute an envelope to recipients who have not actioned it.

Remove Team Member V1Remove a member from a Documenso team.

Update Document AttachmentTool to update an existing document attachment.

Update Document FieldTool to update a single document field's properties in Documenso v2 API.

Update Document Fields BulkTool to update multiple document fields in a single operation.

Update Document Recipient V2Tool to update a document recipient using the v2 API.

Update Document V2Update document properties like title, visibility, and signing settings.

Update EnvelopeUpdate envelope properties like title, visibility, and signing settings.

Update Envelope AttachmentTool to update an existing envelope attachment.

Update Envelope Fields BulkTool to update multiple envelope fields in a single request.

Update Envelope Items BulkTool to update multiple envelope items in a single request.

Update FolderUpdate properties of an existing folder including name, pinned status, parent folder, and visibility.

Update TemplateUpdate template properties like title, visibility, and signing settings.

Update Template Fields BulkTool to update multiple template fields in a single operation.

Update Template RecipientTool to update a template recipient.

Update Template Recipients BulkTool to update multiple template recipients in a single API call.

Use Template (v2-beta)Tool to create a document from a template.

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:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
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: ["documenso"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Documenso 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 Documenso-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 Documenso 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 documenso, 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 Documenso 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 Documenso 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: ["documenso"],
  });

  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 documenso, 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 Documenso 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 Documenso MCP Agent with another framework

OpenAI Agents SDK

Use Documenso MCP with OpenAI Agents SDK

Claude Agent SDK

Use Documenso MCP with Claude Agent SDK

Claude Code

Use Documenso MCP with Claude Code

Claude Cowork

Use Documenso MCP with Claude Cowork

Codex

Use Documenso MCP with Codex

OpenClaw

Use Documenso MCP with OpenClaw

Hermes

Use Documenso MCP with Hermes

CLI

Use Documenso MCP with CLI

Google ADK

Use Documenso MCP with Google ADK

LangChain

Use Documenso MCP with LangChain

Mastra AI

Use Documenso MCP with Mastra AI

LlamaIndex

Use Documenso MCP with LlamaIndex

CrewAI

Use Documenso MCP with CrewAI

Explore Other Toolkits

Google Drive

Oauth2

Google Drive is a cloud storage platform for uploading, sharing, and collaborating on files. It's perfect for keeping your documents accessible and organized across devices.

Google Docs

Oauth2

Google Docs is a cloud-based word processor that enables document creation and real-time collaboration. Its seamless sharing and version history make team editing and content management a breeze.

Google Super

Oauth2Api Key

Google Super is an all-in-one suite combining Gmail, Drive, Calendar, Sheets, Analytics, and more. It gives you a unified platform to manage your digital life, boosting productivity and organization.

TOOLKIT MARKETPLACE

FAQ

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

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

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

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

Used by agents from

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for free Get a demo↗

Harsha GaddipatiCo-founder, Slashy

Karan skipped his own birthday party to fix our critical issue. It was 10 pm and he diverted his Waymo to help us instead. This really sets the bar, shows you the commitment you need to have when users rely on your software.

Abhi AryaCo-founder, Opennote

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it has immensely helped in keeping new users on the platform.

Nirman DaveCEO, Zams

We chose Composio over Pipedream because it delivered depth where it mattered. It supported niche tools and tricky edge cases that other platforms simply ignored. Giving us confidence to scale without compromising.

Ryan YuFounder, Extra Thursday

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down in the complexities of managing agent auth would have been a death sentence for Extra Thursday.

Tomisin JenrolaFounder & CEO, SwarmZero

Before partnering with Composio, adding tool integrations was a slow, resource-intensive process. Each integration could take weeks or months of engineering time, and maintaining them meant constantly keeping up with API changes.

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

How to integrate Documenso MCP with Vercel AI SDK v6

Table of Contents

Connect Documenso without Auth hassles

Introduction

Also integrate Documenso with

TL;DR

What is Vercel AI SDK?

What is the Documenso MCP server, and what's possible with it?

Supported Tools & Triggers

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

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install required dependencies

Set up environment variables

Import required modules and validate environment

Create Tool Router session and initialize MCP client

Connect to MCP server and retrieve tools

Initialize conversation and CLI interface

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

Complete Code

Conclusion

How to build Documenso MCP Agent with another framework

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

OpenClaw

Hermes

CLI

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

Explore Other Toolkits

Google Drive

Google Docs

Google Super

FAQ

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

Can I use Tool Router MCP with Vercel AI SDK v6?

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

How safe is my data with Composio Tool Router?

Used by agents from

Never worry about agent reliability