SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Ignisign MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Ignisign MCP. Start a new signature request for a contract, add a new signer to this application, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Ignisign logoIgnisign
Api Key

Ignisign is an electronic signature platform for secure online document signing and management. Streamline agreements and digital paperwork with advanced workflow tools.

32 Tools

Introduction

This guide walks you through connecting Ignisign to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Ignisign agent that can create and publish signature requests, add signers, upload documents, download signed documents, and manage webhooks through natural language commands.

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

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

Also integrate Ignisign with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The Ignisign MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ignisign account. It provides structured and secure access to your electronic signature workflows, so your agent can perform actions like sending signature requests, managing documents, onboarding signers, and handling signature operations on your behalf.

  • Automated signature request management: Let your agent create, cancel, or delete signature requests, streamlining the entire e-signature process from start to finish.
  • Document initialization and deletion: Have the agent initialize new documents for signing or permanently delete documents when they're no longer needed.
  • Signer onboarding and removal: Effortlessly add new signers to your application environment or remove existing ones as your workflows change.
  • Webhook endpoint management: Allow your agent to create or delete webhook endpoints, enabling real-time notifications and integrations for signature events.
  • Application context retrieval: Fetch global application settings and environment configurations so your agent always works with up-to-date information.

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: ["ignisign"],
  });

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

  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 ignisign, 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 Ignisign 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 Ignisign action and event your agent gets out of the box.

Ignisign API Authentication

Tool to authenticate an application over Ignisign API and retrieve a JWT.

Cancel Signature Request

Cancel (close) a signature request to terminate it.

Initialize Document

Tool to initialize a document for a signature request.

Create Signer

Tool to create a new signer.

Create Webhook Endpoint

Tool to create a new webhook endpoint for an application.

Delete Document

Tool to delete a specific document by its ID.

Delete Ignisign Signature Request

Permanently deletes a signature request from Ignisign by its ID.

Delete Signer

Tool to revoke/delete a signer from an Ignisign application environment.

Delete Webhook Endpoint

Deletes a webhook endpoint by ID.

Get application context

Tool to retrieve the global context of an application.

Get Document Information

Tool to retrieve document metadata by ID.

Get Missing Signer Inputs

Retrieve missing inputs for a signer and profile.

Get Signature Request Details

Tool to retrieve detailed information for a specific signature request.

Get Signature Request Document

Downloads a document's original file.

Get Signature Requests

Retrieves a paginated list of signature requests for a specific Ignisign application and environment.

Get Signed Document

Tool to download the signed document (signature proof) for a signature request.

Get Signer Input Constraints

Tool to get signer input constraints.

Get Signer Inputs

Retrieve available signer input values from a signature request's context.

Get Signer Profile

Retrieve detailed information about a specific signer profile by its ID.

Get Signer Profiles

Retrieve all signer profiles for a specific Ignisign application environment.

Get Webhooks

Retrieves all webhook endpoints configured for a specific Ignisign application environment.

Initialize Ignisign Signature Request

Initialize a new signature request in Ignisign.

List Documents

Tool to retrieve documents linked to a signature request.

Provide Document Content Data JSON

Provides JSON content to an existing document in Ignisign.

Provide Document Content File

Tool to provide file content for a document.

Provide Document Content Private File

Provides private document content by submitting its SHA-256 hash to IgniSign.

Publish Signature Request

Tool to publish a draft signature request.

Search Signers

Tool to search for signers within an application environment with pagination support.

Update Document Information

Tool to update document metadata.

Update Signature Request

Tool to partially update a signature request in DRAFT state.

Update Signer

Updates an existing signer's profile assignment.

Update Webhook Endpoint

Updates an existing webhook endpoint's destination URL and optionally its description.

FRAMEWORKS

How to build Ignisign MCP Agent with another framework

Claude Code logo

Claude Code

Use Ignisign MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Ignisign MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Ignisign MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Ignisign MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Ignisign MCP with Grok Bot

Codex logo

Codex

Use Ignisign MCP with Codex

OpenClaw logo

OpenClaw

Use Ignisign MCP with OpenClaw

Hermes logo

Hermes

Use Ignisign MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Ignisign MCP with Atomic Agent

Google ADK logo

Google ADK

Use Ignisign MCP with Google ADK

LangChain logo

LangChain

Use Ignisign MCP with LangChain

Mastra AI logo

Mastra AI

Use Ignisign MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Ignisign MCP with LlamaIndex

CrewAI logo

CrewAI

Use Ignisign MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Ignisign MCP with Pydantic AI

AutoGen logo

AutoGen

Use Ignisign MCP with AutoGen

FAQ

Frequently asked questions

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

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

Start with Ignisign.It takes 30 seconds.

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

Start building