How to integrate Botpress MCP with LlamaIndex

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

30 min · no commitment · see it on your stack

Botpress logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Botpress to LlamaIndex using the Composio tool router. By the end, you'll have a working Botpress agent that can list all active conversations for your bot, show issues reported for a specific bot, delete a file from a bot workspace through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Botpress account through Composio's Botpress MCP server.

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

Also integrate Botpress 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 Botpress
  • Connect LlamaIndex to the Botpress MCP server
  • Build a Botpress-powered agent using LlamaIndex
  • Interact with Botpress 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 Botpress MCP server, and what's possible with it?

The Botpress MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Botpress account. It provides structured and secure access to your chatbot platform, so your agent can perform actions like listing conversations, managing bot files, tracking issues, and exploring workspaces on your behalf.

  • Comprehensive conversation management: Retrieve and paginate through all chatbot conversations, making it easy to review chat history and analyze user interactions.
  • Bot issue tracking and diagnostics: List and investigate issues related to specific bots, helping you stay informed about errors or configuration problems as they arise.
  • Workspace discovery and organization: Browse both public and private workspaces, making it seamless to manage your bot environments or explore new collaborative spaces.
  • File and tag oversight: List, manage, and categorize bot files and their associated tags or tag values, streamlining bot asset organization.
  • Account information access: Instantly fetch authenticated account details so your agent always works with the latest profile and permission data.

Supported Tools & Triggers

Tools
Break Down Workspace Usage By BotTool to break down workspace usage by bot.
BOTPRESS_CHARGE_WORKSPACE_UNPAID_INVOICESTool to charge unpaid invoices for a specific Botpress workspace.
Check Handle AvailabilityTool to check if a workspace handle is available in Botpress.
BOTPRESS_CREATE_ADMIN_INTEGRATIONTool to create a new integration in a Botpress workspace via the Admin API.
BOTPRESS_CREATE_ADMIN_WORKSPACETool to create a new workspace in Botpress via the Admin API.
BOTPRESS_CREATE_BOTTool to create a new bot in a Botpress workspace via the Admin API.
BOTPRESS_CREATE_CONVERSATIONTool to create a new conversation in Botpress via the Runtime API.
Delete Admin WorkspaceTool to permanently delete a workspace from Botpress admin.
Delete FilePermanently deletes a file from a Botpress bot's storage by its file ID.
Delete Integration Shareable IDTool to delete a shareable ID for an integration installed in a Botpress bot.
Delete Knowledge BasePermanently deletes a knowledge base from Botpress by its knowledge base ID.
Get AccountTool to get details of the authenticated account.
Get Account PreferenceTool to get a preference of the account.
Get All Workspace Quota CompletionTool to get a map of workspace IDs to their highest quota completion rate.
Get Dereferenced Public Plugin By IDTool to get a public plugin by ID with all interface entity references resolved to the corresponding entities as extended by the backing integrations.
Get IntegrationTool to get a specific Botpress integration by name and version.
Get Public IntegrationTool to retrieve a public integration by name and version from the Botpress hub.
Get Public Integration By IDTool to retrieve detailed information about a public Botpress integration by its ID.
Get Public InterfaceTool to get a public interface by name and version from the Botpress Hub.
Get Public Interface by IDTool to retrieve a public interface by its ID from the Botpress Hub.
Get Public PluginTool to retrieve detailed information about a public plugin from Botpress Hub by name and version.
Get Public Plugin By IDTool to retrieve details of a public plugin by its unique ID.
Get Public Plugin CodeTool to retrieve public plugin code from Botpress Hub.
Get Table RowTool to fetch a specific row from a table using the row's unique identifier.
Get Upcoming InvoiceTool to get the upcoming invoice for a workspace.
Get WorkspaceTool to get detailed information about a specific Botpress workspace by ID.
Get Workspace QuotaTool to get workspace quota information for a specific usage type.
LIST_ACTION_RUNSTool to list action runs for a specific integration of a bot.
LIST_BOT_ISSUESTool to list issues associated with a specific bot.
LIST_CONVERSATIONSTool to list all Conversations.
LIST_FILE_TAGSTool to list all tags used across all bot files.
LIST_FILE_TAG_VALUESTool to list all values for a given file tag across all files.
LIST_HUB_INTEGRATIONSTool to list public integrations from the Botpress hub.
LIST_INTEGRATION_API_KEYSTool to list Integration API Keys (IAKs) for a specific integration.
List IntegrationsTool to list integrations with filtering and sorting capabilities.
LIST_KNOWLEDGE_BASESTool to list knowledge bases for a bot.
List PluginsTool to list Botpress plugins.
List Public InterfacesTool to retrieve a list of public interfaces available in the Botpress Hub.
LIST_PUBLIC_PLUGINSTool to retrieve a list of public plugins available in the Botpress hub.
LIST_PUBLIC_WORKSPACESTool to retrieve a list of public workspaces.
LIST_USAGE_HISTORYTool to retrieve usage history for a bot or workspace.
List Workspace InvoicesTool to list all invoices billed to a workspace.
LIST_WORKSPACESList all Botpress workspaces accessible to the authenticated user.
Request Integration VerificationTool to request verification for a Botpress integration via the Admin API.
BOTPRESS_RUN_VRLTool to execute a VRL (Vector Remap Language) script against input data using the Botpress Admin API.
BOTPRESS_SEND_MESSAGETool to send a message to an existing Botpress conversation via the Runtime API.
Set Account PreferenceTool to set a preference for the account.
Set Workspace PreferenceTool to set a preference for a Botpress workspace.
Update AccountTool to update details of the authenticated account.
BOTPRESS_UPDATE_ADMIN_BOTSTool to update an existing bot in a Botpress workspace via the Admin API.
UPDATE_ADMIN_WORKSPACETool to update a Botpress workspace via the Admin API.
BOTPRESS_UPDATE_WORKFLOWTool to update a workflow object in Botpress by setting parameter values.
BOTPRESS_VALIDATE_INTEGRATION_UPDATETool to validate an integration update request in Botpress Admin API.

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 Botpress account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Botpress

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 Botpress 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 botpress_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=["botpress"],
    )

    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 Botpress actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Botpress 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, botpress)
  • 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 Botpress 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 Botpress 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 Botpress

Run the agent

npx ts-node llamaindex-agent.ts

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

Complete Code

Here's the complete code to get you started with Botpress 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=["botpress"],
    )

    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 Botpress actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Botpress 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 Botpress to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Botpress 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 Botpress MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Botpress MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Botpress MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Botpress MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Botpress MCP with Claude Cowork

Codex logo

Codex

Use Botpress MCP with Codex

OpenClaw logo

OpenClaw

Use Botpress MCP with OpenClaw

Hermes logo

Hermes

Use Botpress MCP with Hermes

CLI logo

CLI

Use Botpress MCP with CLI

Google ADK logo

Google ADK

Use Botpress MCP with Google ADK

LangChain logo

LangChain

Use Botpress MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Botpress MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Botpress MCP with Mastra AI

CrewAI logo

CrewAI

Use Botpress MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Botpress 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 Botpress 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↗