How to integrate Dropbox sign MCP with Pydantic AI

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Dropbox sign logo
Pydantic AI logo
divider

Introduction

This guide walks you through connecting Dropbox sign to Pydantic AI using the Composio tool router. By the end, you'll have a working Dropbox sign agent that can send nda for signature to new hire, get status of recent signature requests, download signed contract from last week through natural language commands.

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

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

Also integrate Dropbox sign with

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Dropbox sign
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Dropbox sign workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

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

The Dropbox sign MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Dropbox Sign account. It provides structured and secure access to your e-signature workflows, so your agent can prepare signature requests, manage documents, track signing progress, and automate agreement workflows on your behalf.

  • Automated signature requests: Have your agent create, send, and manage legally binding signature requests to one or multiple recipients, streamlining document approval processes.
  • Template-based document preparation: Let your agent generate documents from templates, pre-fill fields, and quickly send out repeat agreements without manual editing.
  • Status tracking and reminders: Ask your agent to monitor the progress of signature requests, check who has signed, and send automated reminders to outstanding signers as needed.
  • Secure document storage and retrieval: Effortlessly fetch completed, pending, or archived documents, download signed agreements, and keep your workflow organized and compliant.
  • Audit trails and activity logs: Access detailed audit trails and event histories for every document, so you can maintain compliance and always know who did what, and when.

Supported Tools & Triggers

Tools
Invite User to TeamTool to invite a user to your Team.
Add User to TemplateTool to grant a specified account access to a template.
Bulk create embedded signature request with templateTool to create a BulkSendJob for embedded templated signature requests.
Bulk send with templateTool to create a BulkSendJob for templated signature requests.
Cancel Signature RequestCancels an incomplete signature request.
Create Dropbox Sign AccountTool to create a new Dropbox Sign account associated with a specified email address.
Create API AppTool to create a new Dropbox Sign API App.
Create Embedded Signature RequestTool to create an embedded signature request for signing in an iFrame.
Create Embedded Signature Request With TemplateTool to create an embedded signature request based on a template.
Create Embedded Template DraftTool to create an embedded template draft.
Create Embedded Unclaimed Draft with TemplateTool to create an embedded unclaimed draft using saved templates.
Create ReportRequest creation of CSV report(s) for a specified date range.
Create TemplateTool to create a reusable template for document signing workflows.
Create Unclaimed DraftTool to create an unclaimed draft that can be claimed via a unique URL.
Delete API AppTool to delete an API App from your Dropbox Sign account by its client_id.
Delete FaxTool to delete a fax from the system by its fax_id.
Delete TemplatePermanently deletes a template from your Dropbox Sign account by its template_id.
Download Signature Request FilesDownload files for a signature request as PDF (merged) or ZIP (individual documents).
Edit and Resend Embedded Signature RequestTool to edit and resend an embedded signature request.
Edit and Resend Signature RequestEdits and resends an existing non-templated signature request with updated documents, signers, or settings.
Edit and Resend Unclaimed DraftTool to edit and resend a previously created unclaimed draft.
Edit and Resend Embedded Signature Request With TemplateTool to edit and resend an embedded signature request using templates.
Get Dropbox Sign AccountRetrieves detailed information about a Dropbox Sign account including quotas, payment status, and settings.
Get API AppTool to retrieve information about an API App by its client ID.
Get Bulk Send JobTool to retrieve the status of a bulk send job.
Get Current Team MembershipTool to get the current team membership status and details.
Get Embedded Sign URLRetrieves an embedded signing URL for a specific signer's signature.
Get Embedded Template Edit URLTool to generate an edit URL for embedded template editing.
Get Available Fax Line Area CodesTool to retrieve available fax line area codes for a given country, state/province, and city.
Get Signature RequestRetrieves the current status and complete details of a signature request by ID.
Get Signature Request Files as Data URITool to download signature request files as a base64-encoded data URI.
Get Signature Request Files as File URLRetrieves a copy of the current documents and returns a JSON object with a URL to the file (PDFs only).
Get Team InfoRetrieves information about a Dropbox Sign team, including team name, member count, and sub-team count.
Get TemplateTool to return the specified template.
Download Template FilesTool to download documents associated with a template.
Get Template Files as Data URITool to retrieve template documents as base64-encoded data URI.
Get Template Files as File URLTool to retrieve a copy of template documents and return a JSON object with a URL to the file (PDFs only).
List API AppsTool to list API Apps.
List Bulk Send JobsTool to list bulk send jobs.
List FaxesTool to list faxes and their properties.
List Fax LinesTool to list fax lines and their properties.
List Signature RequestsTool to list signature requests.
List Sub-TeamsLists all sub-teams belonging to a parent team with pagination support.
List Team MembersLists all members and their roles for a specific team.
List All TeamsLists all Dropbox Sign teams accessible to the authenticated user, including the current team and its sub-teams.
List TemplatesTool to list templates.
Generate OAuth Authorization URLTool to generate an OAuth authorization URL.
Release Signature Request HoldRelease a held signature request to send it to signers.
Remove User from TemplateTool to remove an account's access to a template.
Send Signature RequestTool to create and send a new signature request with documents.
Send Request ReminderSends an email reminder to a signer about a pending signature request.
Update Dropbox Sign AccountTool to update Dropbox Sign account properties and settings.
Update API AppTool to update an existing API App in Dropbox Sign.
Update Signature RequestUpdates the email address and/or name for a specific signer on a signature request.
Update Template FilesTool to update files for an existing template.
Verify Dropbox Sign AccountTool to verify whether a Dropbox Sign account exists for the given email.

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

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming

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 pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Dropbox sign
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file

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

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Dropbox sign
  • MCPServerStreamableHTTP connects to the Dropbox sign MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Dropbox sign
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["dropbox_sign"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Dropbox sign tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
dropbox_sign_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[dropbox_sign_mcp],
    instructions=(
        "You are a Dropbox sign assistant. Use Dropbox sign tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Dropbox sign endpoint
  • The agent uses GPT-5 to interpret user commands and perform Dropbox sign operations
  • The instructions field defines the agent's role and behavior

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Dropbox sign.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Dropbox sign API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Dropbox sign and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Dropbox sign
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["dropbox_sign"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    dropbox_sign_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[dropbox_sign_mcp],
        instructions=(
            "You are a Dropbox sign assistant. Use Dropbox sign tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Dropbox sign.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Dropbox sign through Composio's Tool Router. With this setup, your agent can perform real Dropbox sign actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Dropbox sign for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.

How to build Dropbox sign MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Dropbox sign MCP?

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

Can I use Tool Router MCP with Pydantic AI?

Yes, you can. Pydantic AI 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 Dropbox sign tools.

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

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

Used by agents from

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