How to integrate Documenso MCP with LlamaIndex

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Documenso logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Documenso to LlamaIndex 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 LlamaIndex 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

TL;DR

Here's what you'll learn:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Documenso
  • Connect LlamaIndex to the Documenso MCP server
  • Build a Documenso-powered agent using LlamaIndex
  • Interact with Documenso through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

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:

  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 you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Documenso account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Documenso

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Documenso access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called documenso_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["documenso"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Documenso actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Documenso actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, documenso)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Documenso tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Documenso database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Documenso

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Documenso, then start asking questions.

Complete Code

Here's the complete code to get you started with Documenso and LlamaIndex:

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["documenso"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Documenso actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Documenso actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Documenso to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Documenso tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Documenso MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Documenso MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Documenso MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Documenso MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Documenso MCP with Claude Cowork

Codex logo

Codex

Use Documenso MCP with Codex

OpenClaw logo

OpenClaw

Use Documenso MCP with OpenClaw

Hermes logo

Hermes

Use Documenso MCP with Hermes

CLI logo

CLI

Use Documenso MCP with CLI

Google ADK logo

Google ADK

Use Documenso MCP with Google ADK

LangChain logo

LangChain

Use Documenso MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Documenso MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Documenso MCP with Mastra AI

CrewAI logo

CrewAI

Use Documenso MCP with CrewAI

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 LlamaIndex?

Yes, you can. LlamaIndex 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

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.

Get started for freeGet a demo↗
Documenso MCP Integration with LlamaIndex | Composio