How to integrate Docnify MCP with CrewAI

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

Introduction

This guide walks you through connecting Docnify to CrewAI using the Composio tool router. By the end, you'll have a working Docnify agent that can list all documents awaiting my signature, add recipient to contract with specific email, resend nda document to all unsigned recipients, delete expired document from my docnify account through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Docnify account through Composio's Docnify 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 Docnify connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Docnify
  • Build a conversational loop where your agent can execute Docnify 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 Docnify MCP server, and what's possible with it?

The Docnify MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Docnify account. It provides structured and secure access to your digital signing workflows, so your agent can perform actions like listing documents, adding recipients, creating document fields, and resending signature requests on your behalf.

  • Seamless document management: Let your agent list, fetch, or delete documents in your Docnify account to keep your workspace organized and up to date.
  • Effortless recipient handling: Automatically add or remove recipients from documents, manage their signing order, and control access with a single prompt.
  • Custom field creation and editing: Direct your agent to add or remove fields—like signature, initials, or dates—on documents before sending them out for signing.
  • Template automation: Quickly list available templates or fetch template details, letting your agent streamline the process of generating new documents.
  • Signature request management: Easily resend signature requests or notifications, ensuring signers don’t miss important documents and deadlines.

Supported Tools & Triggers

Tools
Add Document RecipientTool to add a recipient to a document.
Create Document FieldsTool to create one or more fields on a document.
Delete DocumentTool to delete a specific document by its ID.
Delete Document FieldTool to delete a field from a document.
Delete document recipientTool to remove a recipient from a document.
Get DocumentTool to fetch a specific document by its ID.
Get TemplateTool to fetch a specific template by its ID.
List DocumentsTool to list documents in the Docnify account.
List TemplatesTool to list templates in the Docnify account.
Resend DocumentTool to resend a document for signing.
Send DocumentTool to send a document for signing.
Update Document FieldsTool to update metadata of document fields.
Update Document RecipientTool to update a recipient's details (name, email, role) on a document.

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 Docnify 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 Docnify 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 Docnify MCP URL

Create a Composio Tool Router session for Docnify

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["docnify"],
)
url = session.mcp.url
What's happening:
  • You create a Docnify only session through Composio
  • Composio returns an MCP HTTP URL that exposes Docnify 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="Docnify Assistant",
    goal="Help users interact with Docnify through natural language commands",
    backstory=(
        "You are an expert assistant with access to Docnify tools. "
        "You can perform various Docnify 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 Docnify 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 Docnify 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 Docnify 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_docnify_agent.py

Complete Code

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

python
# file: crewai_docnify_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 Docnify session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["docnify"],
    )
    url = session.mcp.url

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

    # Create Docnify assistant agent
    toolkit_agent = Agent(
        role="Docnify Assistant",
        goal="Help users interact with Docnify through natural language commands",
        backstory=(
            "You are an expert assistant with access to Docnify tools. "
            "You can perform various Docnify 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 Docnify 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 Docnify 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 Docnify through Composio's Tool Router. The agent can perform Docnify 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 Docnify MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Docnify MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Docnify MCP with Claude Agent SDK

Google ADK

Google ADK

Use Docnify MCP with Google ADK

LangChain

LangChain

Use Docnify MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Docnify MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Docnify MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Docnify MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Docnify 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 Docnify 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