How to integrate Ignisign MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Ignisign Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Ignisign to CrewAI using the Composio tool router. By the end, you'll have a working Ignisign agent that can start a new signature request for a contract, add a new signer to this application, delete a completed document by its id, create a webhook to track signature events through natural language commands.

This guide will help you understand how to give your CrewAI 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.

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Ignisign connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Ignisign
  • Build a conversational loop where your agent can execute Ignisign operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

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.

Supported Tools & Triggers

Tools
Ignisign API AuthenticationTool to authenticate an application over Ignisign API and retrieve a JWT.
Cancel Signature RequestTool to cancel a signature request.
Initialize DocumentTool to initialize a document for a signature request.
Create SignerTool to create a new signer.
Create Webhook EndpointTool to create a new webhook endpoint for an application.
Delete DocumentTool to delete a specific document by its ID.
Delete Ignisign Signature RequestTool to delete a signature request.
Delete SignerTool to delete a signer.
Delete Webhook EndpointTool to delete a specific webhook endpoint.
Get application contextTool to retrieve the global context of an application.
Get Document InformationTool to retrieve document metadata by ID.
Get Missing Signer InputsTool to determine missing inputs needed for a signer in a specific signature profile.
Get Signature Request DetailsTool to retrieve detailed information for a specific signature request.
Get Signature Request DocumentTool to retrieve the document associated with a specific signature request.
Get Signature RequestsTool to retrieve a paginated list of signature requests for an application.
Get Signature Request StatusTool to retrieve the current status of a specific signature request.
Get Signed DocumentTool to download the signed document (signature proof) for a signature request.
Get Signer Creation ConstraintsTool to retrieve input constraints required to create a signer for a specific signature profile.
Get Signer Input ConstraintsTool to get signer input constraints.
Get Signer InputsTool to retrieve inputs provided by a signer for a signature request.
Get Signer ProfileTool to retrieve a signer profile.
Get Signer ProfilesTool to retrieve signer profiles.
Get Webhook DetailsTool to retrieve details of a specific webhook endpoint.
Get WebhooksTool to list all webhook endpoints configured for an application environment.
Close Ignisign Signature RequestTool to close an active signature request.
Update SignerTool to update details of an existing signer.
Initialize Ignisign Signature RequestTool to initialize a new signature request.
List DocumentsTool to retrieve documents linked to a signature request.
Provide Document Content Data JSONTool to provide JSON content for a document.
Provide Document Content FileTool to provide file content for a document.
Provide Document Content Private FileTool to provide private content for a document via its SHA-256 hash.
Publish Signature RequestTool to publish a draft signature request.
Search SignersTool to search for signers within an application.
Update Document InformationTool to update document metadata.
Update Signature RequestTool to partially update a signature request in DRAFT state.
Update Webhook EndpointTool to update an existing webhook endpoint.

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 starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Ignisign connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

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 dependencies

bash
pip install composio crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Ignisign via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Ignisign MCP URL

Create a Composio Tool Router session for Ignisign

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["ignisign"],
)
url = session.mcp.url
What's happening:
  • You create a Ignisign only session through Composio
  • Composio returns an MCP HTTP URL that exposes Ignisign tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Ignisign Assistant",
    goal="Help users interact with Ignisign through natural language commands",
    backstory=(
        "You are an expert assistant with access to Ignisign tools. "
        "You can perform various Ignisign operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Ignisign MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Ignisign operations.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Ignisign related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_ignisign_agent.py

Complete Code

Here's the complete code to get you started with Ignisign and CrewAI:

python
# file: crewai_ignisign_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Ignisign session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["ignisign"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Ignisign assistant agent
    toolkit_agent = Agent(
        role="Ignisign Assistant",
        goal="Help users interact with Ignisign through natural language commands",
        backstory=(
            "You are an expert assistant with access to Ignisign tools. "
            "You can perform various Ignisign operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Ignisign operations.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Ignisign related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Ignisign through Composio's Tool Router. The agent can perform Ignisign operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Ignisign MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Ignisign MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Ignisign MCP with Claude Agent SDK

Google ADK

Google ADK

Use Ignisign MCP with Google ADK

LangChain

LangChain

Use Ignisign MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Ignisign MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Ignisign MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Ignisign MCP with LlamaIndex

FAQ

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

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.

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI 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.

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

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.

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 Ignisign data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
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