How to integrate Capsule crm MCP with LlamaIndex

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Capsule crm logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Capsule crm to LlamaIndex using the Composio tool router. By the end, you'll have a working Capsule crm agent that can add new company and contact details, list all open tasks for today, show all projects started this month through natural language commands.

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

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

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

The Capsule crm MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Capsule CRM account. It provides structured and secure access to your contacts, sales opportunities, tasks, and more, so your agent can perform actions like managing contacts, tracking projects, organizing tasks, and retrieving sales data on your behalf.

  • Contact and party management: Effortlessly create new contacts or organizations, list all parties, and even delete records when needed—all through your agent.
  • Sales opportunity tracking: Retrieve lists of deleted or restricted sales opportunities and keep your pipeline data up to date with minimal manual work.
  • Task and activity organization: List, search, and manage your Capsule tasks, notes, and completed activities to stay on top of daily work.
  • Project and case monitoring: Quickly fetch all ongoing or filtered projects (cases) and review their status or details without ever opening the web app.
  • Team and user management: List all users on your Capsule account or pull employees for a specific organization, making team reporting and auditing a breeze.

Supported Tools & Triggers

Tools
Add Project PartyTool to add a party (person or organisation) to a project in Capsule CRM.
Create Capsule CRM CategoryTool to create a new task category in Capsule CRM.
Create Custom Field DefinitionTool to create a new custom field definition for parties, opportunities, or projects in Capsule CRM.
Create EntryTool to create a new note entry in Capsule CRM.
Create Lost ReasonTool to create a new lost reason in Capsule CRM.
Create Capsule CRM MilestoneTool to create a new milestone in Capsule CRM.
Create OpportunityTool to create a new opportunity in Capsule CRM.
Add Party to OpportunityTool to add a party (person or organisation) to an opportunity in Capsule CRM.
Create Capsule CRM PartyTool to create a Party in Capsule CRM.
Create ProjectTool to create a new project (case) in Capsule CRM.
Create StageTool to create a new stage in a board in Capsule CRM.
Create TaskTool to create a new task in Capsule CRM.
Create Capsule CRM TitleTool to create a new custom person title in Capsule CRM.
Create TrackTool to create a new track in Capsule CRM by applying a track definition to a project or opportunity.
Create Track DefinitionTool to create a new track definition in Capsule CRM.
Delete BoardTool to delete (archive) a specific board in Capsule CRM.
Delete CategoryTool to delete a category from Capsule CRM.
Delete Custom Field DefinitionTool to delete a custom field definition from an entity type in Capsule CRM.
Delete Entity TagTool to delete a tag from an entity type (parties, opportunities, or kases) in Capsule CRM.
Delete EntryTool to delete an entry (note, email, or task) from Capsule CRM.
Delete Lost ReasonTool to delete a lost reason from Capsule CRM.
Delete MilestoneTool to delete a specific milestone from Capsule CRM.
Delete OpportunityTool to delete an opportunity from Capsule CRM.
Delete Opportunity PartyTool to remove a party (person or organisation) from an opportunity in Capsule CRM.
Delete PartyTool to fully delete a specific party (person or organisation) from Capsule CRM.
Delete ProjectTool to delete a project (case) from Capsule CRM.
Delete Project PartyTool to remove a party (person or organisation) from a project in Capsule CRM.
Delete StageTool to delete a specific stage from a board in Capsule CRM.
Delete TaskTool to delete a specific task from Capsule CRM.
Delete TitleTool to delete a specific title from Capsule CRM.
Delete TrackTool to delete a specific track from Capsule CRM.
Delete Track DefinitionTool to delete a specific track definition from Capsule CRM.
Get Activity TypeTool to get a specific activity type by ID.
Get AttachmentTool to retrieve a specific attachment by ID from Capsule CRM.
Get BoardTool to get a specific board by ID from Capsule CRM.
Get CategoryTool to get a specific category by ID.
Get Current UserTool to retrieve the current authenticated user's details including id, username, name, locale, currency, status, timezone, lastLoginAt, and taskReminder settings.
Get Custom Field DefinitionTool to get a specific custom field definition by ID from Capsule CRM.
Get Entity TagTool to retrieve a specific tag by ID for an entity type (parties, opportunities, or kases) in Capsule CRM.
Get EntryTool to retrieve a specific entry by ID.
Get Lost ReasonTool to retrieve a specific lost reason by ID from Capsule CRM.
Get MilestoneTool to get a specific milestone by ID from Capsule CRM.
Get OpportunityTool to retrieve a specific opportunity by its ID from Capsule CRM.
Get PipelineTool to get a specific pipeline by ID from Capsule CRM.
Get ProjectTool to retrieve a specific project (case) by its ID from Capsule CRM.
Get StageTool to get a specific stage by ID from Capsule CRM.
Get TaskTool to get a specific task by ID.
Get TrackTool to get a specific track by ID.
Get Track DefinitionTool to get a specific track definition by ID from Capsule CRM.
Get UserTool to get a specific user by ID.
List Activity Type IconsTool to list available activity type icons in Capsule CRM.
List Activity TypesTool to list all activity types on the Capsule account.
List BoardsTool to list all boards on the Capsule CRM account.
List Board StagesTool to list stages associated with a board in Capsule CRM.
List CategoriesTool to list all task categories on the Capsule account.
List CountriesTool to list all countries on the Capsule CRM account.
List CurrenciesTool to list all available currencies on the Capsule account.
List Custom Field DefinitionsTool to list all custom field definitions for parties, opportunities, or projects (kases).
List Deleted OpportunitiesTool to list opportunities deleted or restricted since a given date.
List deleted partiesTool to retrieve parties deleted since a given date.
List Deleted ProjectsTool to list projects deleted or restricted since a given date.
List Entity EntriesTool to list entries (notes, emails, tasks) for a specific party, opportunity, or project.
List Entity TagsTool to list all tag definitions for a specific entity type (parties, opportunities, or kases).
List Entity TracksTool to list tracks applied to a specific opportunity or project.
List Entries By DateTool to list notes, emails, and completed party tasks in descending order by entry date.
List GoalsTool to list all goals on the Capsule account.
List Lost ReasonsTool to list all lost reasons on the Capsule account.
List MilestonesTool to list all milestones on the Capsule account.
List OpportunitiesTool to list all opportunities from Capsule CRM with pagination and filtering.
List Opportunity PartiesTool to list additional parties associated with an opportunity in Capsule CRM.
List Opportunity ProjectsTool to list projects (cases) associated with a specific opportunity in Capsule CRM.
List Organisation EmployeesTool to list employees linked to a specific organisation (party).
List PartiesTool to list all parties (contacts) on the account.
List Party OpportunitiesTool to list all opportunities associated with a specific party in Capsule CRM.
List Party ProjectsTool to list projects associated with a specific party in Capsule CRM.
List Pipeline MilestonesTool to list milestones associated with a specific pipeline in Capsule CRM.
List PipelinesTool to list all sales pipelines on the Capsule account.
List Project PartiesTool to list parties associated with a specific project in Capsule CRM.
List ProjectsList projects (cases) from Capsule CRM with pagination and filtering options.
List REST HooksTool to list all REST hook subscriptions on the Capsule CRM account.
List SiteTool to retrieve site (account) information for the authenticated Capsule CRM account.
List StagesTool to list all stages on the Capsule CRM account.
List TasksTool to list tasks on the Capsule account.
List TeamsTool to list all teams on the Capsule CRM account.
List TitlesTool to list all custom person titles on the Capsule account.
List Track DefinitionsTool to list all track definitions on the Capsule account.
List UsersList all users on the Capsule CRM account.
Restore BoardTool to restore a deleted board in Capsule CRM.
Run Filter QueryTool to run structured filter queries on parties, opportunities or kases.
Search OpportunitiesTool to search for opportunities in Capsule CRM by query string.
Search PartiesTool to search for parties (contacts/organisations) in Capsule CRM by query string.
Search ProjectsTool to search for projects (cases) in Capsule CRM by query string.
Update Capsule CRM BoardTool to update an existing board in Capsule CRM.
Update Capsule CRM CategoryTool to update an existing category in Capsule CRM.
Update Custom Field DefinitionTool to update an existing custom field definition in Capsule CRM.
Update Entity TagTool to update an existing tag for an entity type (parties, opportunities, or kases) in Capsule CRM.
Update EntryTool to update an existing entry (note, email, or task) in Capsule CRM.
Update Capsule CRM Lost ReasonTool to update an existing lost reason in Capsule CRM.
Update Capsule CRM MilestoneTool to update an existing milestone in Capsule CRM.
Update OpportunityTool to update an existing opportunity in Capsule CRM.
Update Capsule CRM PartyTool to update an existing person or organisation (Party) in Capsule CRM.
Update Capsule CRM PipelineTool to update an existing pipeline in Capsule CRM.
Update ProjectTool to update an existing project (case) in Capsule CRM.
Update Capsule CRM StageTool to update an existing stage in Capsule CRM.
Update TaskTool to update an existing task in Capsule CRM.
Update Capsule CRM TrackTool to update an existing track in Capsule CRM.
Update Capsule CRM Track DefinitionTool to update an existing track definition in Capsule CRM.
Update UserTool to update an existing user in Capsule CRM.
Upload AttachmentTool to upload an attachment to Capsule CRM.

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 Capsule crm account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Capsule crm

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 Capsule crm 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 capsule crm_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=["capsule_crm"],
    )

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

Run the agent

npx ts-node llamaindex-agent.ts

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

Complete Code

Here's the complete code to get you started with Capsule crm 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=["capsule_crm"],
    )

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

FAQ

What are the differences in Tool Router MCP and Capsule crm MCP?

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

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

Yes, absolutely. You can configure which Capsule crm 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 Capsule crm 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.