# How to integrate Apollo MCP with LlamaIndex

```json
{
  "title": "How to integrate Apollo MCP with LlamaIndex",
  "toolkit": "Apollo",
  "toolkit_slug": "apollo",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/apollo/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/apollo/framework/llama-index.md",
  "updated_at": "2026-05-12T10:01:43.872Z"
}
```

## Introduction

This guide walks you through connecting Apollo to LlamaIndex using the Composio tool router. By the end, you'll have a working Apollo agent that can bulk enrich profiles for new leads, add contacts to outreach sequence now, create a new sales deal for acme through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Apollo account through Composio's Apollo MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Apollo with

- [ChatGPT](https://composio.dev/toolkits/apollo/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/apollo/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/apollo/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/apollo/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/apollo/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/apollo/framework/codex)
- [Cursor](https://composio.dev/toolkits/apollo/framework/cursor)
- [VS Code](https://composio.dev/toolkits/apollo/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/apollo/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/apollo/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/apollo/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/apollo/framework/cli)
- [Google ADK](https://composio.dev/toolkits/apollo/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/apollo/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/apollo/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/apollo/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/apollo/framework/crew-ai)

## 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 Apollo
- Connect LlamaIndex to the Apollo MCP server
- Build a Apollo-powered agent using LlamaIndex
- Interact with Apollo 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 Apollo MCP server, and what's possible with it?

The Apollo MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Apollo account. It provides structured and secure access to your CRM and lead generation data, so your agent can create contacts, enrich organizations, manage deals, update account stages, and automate tasks for your sales pipeline—all on your behalf.
- Contact and account creation: Instantly add new contacts or accounts to Apollo, linking them to organizations and stages to keep your CRM up to date with zero manual entry.
- Bulk data enrichment: Rapidly enrich multiple people or organizations at once, leveraging Apollo's database to fill gaps and update your records with the latest information.
- Sales opportunity and pipeline management: Let your agent create new deals, retrieve opportunity stages, and move accounts through your sales funnel to optimize pipeline performance.
- Automated outreach sequencing: Add contacts to email sequences, making it easy to launch targeted campaigns and follow-ups without lifting a finger.
- Task creation and label organization: Generate actionable Apollo tasks for your team and organize contacts or accounts with labels, so nothing slips through the cracks.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `APOLLO_ADD_CONTACTS_TO_SEQUENCE` | Add Contacts to Sequence | Adds contacts to a specified Apollo email sequence and returns the contact details. `sequence_id`, `emailer_campaign_id`, and `send_email_from_email_account_id` must be retrieved from Apollo listing/search endpoints before calling this tool — these IDs cannot be inferred from names. |
| `APOLLO_BULK_ORGANIZATION_ENRICHMENT` | Bulk organization enrichment | Enriches data for up to 10 organizations simultaneously by providing a list of their base company domains (e.g., 'apollo.io', not 'www.apollo.io'). Each call consumes Apollo credits per domain enriched; monitor quota to avoid exhaustion errors. |
| `APOLLO_BULK_PEOPLE_ENRICHMENT` | Bulk people enrichment | Use to enrich multiple person profiles simultaneously with comprehensive data from Apollo's database. Each call consumes Apollo credits; avoid re-enriching the same contacts. Responses may include null or missing fields (e.g., email, phone, organization); treat unmatched records as valid 'no match' outcomes, not errors. Heavy use may trigger HTTP 429; respect Retry-After headers. |
| `APOLLO_BULK_UPDATE_ACCOUNT_STAGE` | Bulk update account stage | Bulk updates the stage for specified existing Apollo.io accounts, moving them to a valid new account stage. |
| `APOLLO_CREATE_ACCOUNT` | Create an Apollo account | Creates a new account in Apollo.io; a new record is created even if a similar account exists, and provided `owner_id` or `account_stage_id` must be valid existing IDs. The response includes the new account's ID, which can be used directly in subsequent calls. |
| `APOLLO_CREATE_BULK_ACCOUNTS` | Bulk create Apollo accounts | Creates multiple accounts in Apollo.io with a single API call (maximum 100 accounts per request). Use when creating multiple company records at once. |
| `APOLLO_CREATE_BULK_CONTACTS` | Bulk create Apollo contacts | Tool to bulk create multiple contacts in Apollo with a single API call. Use when you need to create multiple contacts efficiently. Supports up to 100 contacts per request with optional deduplication. |
| `APOLLO_CREATE_CALL_RECORD` | Create call record in Apollo | Tool to log call records in Apollo from external systems. Use when recording calls made through outside systems like Orum or Nooks; requires a master API key and cannot dial prospects directly. |
| `APOLLO_CREATE_CONTACT` | Create Apollo contact | Creates a new contact in Apollo.io; use `account_id` to link to an organization and `contact_stage_id` for sales stage. Apollo does not auto-deduplicate — duplicate records sharing the same email are silently created; always search via APOLLO_SEARCH_CONTACTS before calling this tool. Requires explicit user confirmation before execution. |
| `APOLLO_CREATE_CUSTOM_FIELD` | Create custom field | Creates a new custom field in Apollo.io for contacts, accounts, or opportunities. Use when you need to define additional data fields beyond Apollo's standard attributes. |
| `APOLLO_CREATE_DEAL` | Create Apollo deal | Creates a new sales opportunity (deal) in Apollo.io; all provided IDs (`owner_id`, `account_id`, `opportunity_stage_id`) must be valid existing Apollo identifiers. This action has persistent side effects — obtain explicit user confirmation before invoking. |
| `APOLLO_CREATE_TASK` | Create Apollo Task | Tool to create a single task in Apollo.io. Use when you need to add a new task to your team's Apollo account for a specific contact. The task will be assigned to a user and includes details like type, status, priority, due date, and optional notes. |
| `APOLLO_GET_ACCOUNT` | Get Account by ID | Tool to retrieve detailed information about a specific account by its Apollo ID. Use when you need to fetch complete account data including company details, contact information, and CRM integration fields. |
| `APOLLO_GET_AUTH_STATUS` | Check Apollo API key status | Tool to check whether the provided Apollo API key is valid and accepted by Apollo (health/auth check). Use when any Apollo endpoint returns 401/403/422 to quickly diagnose invalid/expired keys versus permission scope issues. If this succeeds but other endpoints return 403, it strongly suggests permissioning or master-key scope issues rather than a totally invalid credential. |
| `APOLLO_GET_CONTACT` | Get Apollo Contact | Retrieves detailed information about a specific contact by its ID. Use this to view contact details including name, email, phone numbers, organization, and custom fields. |
| `APOLLO_GET_DEAL` | Get Apollo deal | Retrieves information about a specific deal by its ID. Use this when you need to view details of a single deal. |
| `APOLLO_GET_LABELS` | Get Labels | Retrieves all labels from Apollo.io, used for organizing contacts and accounts. Call this before APOLLO_CREATE_CONTACT or APOLLO_UPDATE_ACCOUNT to validate label values against the returned list; mismatched labels cause 400/422 errors. |
| `APOLLO_GET_OPPORTUNITY_STAGES` | Get opportunity stages | Retrieves all configured opportunity (deal) stages from the Apollo.io account. |
| `APOLLO_GET_ORGANIZATION` | Get Organization by ID | Retrieves complete information about a specific organization by its Apollo ID. Use when you need detailed company data including funding, technologies, employee counts, and more. |
| `APOLLO_GET_ORGANIZATION_JOB_POSTINGS` | Get Organization Job Postings | Retrieves paginated job postings for a specified organization by its ID, optionally filtering by domain; ensure `organization_id` is a valid identifier. |
| `APOLLO_GET_TYPED_CUSTOM_FIELDS` | Get typed custom fields | Retrieves all typed custom field definitions available in the Apollo.io instance, detailing their types and configurations. Call before constructing payloads for APOLLO_UPDATE_CONTACT or APOLLO_UPDATE_ACCOUNT — mismatched types or invalid enum options cause 400 errors. |
| `APOLLO_LIST_ACCOUNT_STAGES` | List Apollo account stages | Retrieves the IDs for all available account stages in your team's Apollo account. |
| `APOLLO_LIST_CONTACT_STAGES` | List apollo contact stages | Retrieves all available contact stages from an Apollo account, including their unique IDs and names. |
| `APOLLO_LIST_DEALS` | List Apollo deals | Retrieves a list of deals from Apollo, using Apollo's default sort order if 'sort_by_field' is omitted. |
| `APOLLO_LIST_EMAIL_ACCOUNTS` | List email accounts | Retrieves all email accounts and their details for the authenticated user; takes no parameters. |
| `APOLLO_LIST_FIELDS` | List Fields | Retrieves all field definitions from Apollo.io, including system fields and custom fields. Use the optional 'source' parameter to filter by field type (system, custom, or crm_synced). |
| `APOLLO_LIST_USERS` | List Apollo Users | Retrieves a list of all users (teammates) associated with the Apollo account, supporting pagination via `page` and `per_page` parameters. Use this to obtain numeric user IDs required by operations like APOLLO_UPDATE_CONTACT_OWNERSHIP — names or email addresses are not accepted in place of these IDs. |
| `APOLLO_ORGANIZATION_ENRICHMENT` | Enrich organization data | Fetches comprehensive organization enrichment data from Apollo.io for a given company domain; results are most meaningful if the company exists in Apollo's database. Each call consumes Apollo credits and may be unavailable on free plans. Returns HTTP 429 under burst usage; use exponential backoff on retries. |
| `APOLLO_ORGANIZATION_SEARCH` | Search organizations in Apollo | Searches Apollo's database for organizations using various filters; consumes credits on every call (unavailable on free plans) — avoid re-running identical queries and surface quota errors rather than retrying. Retrieves a maximum of 50,000 records; uses `page` (1-500) and `per_page` (1-100) for pagination — check `total_pages` in the response to iterate. Overly strict filter combinations can return zero results; start broad and narrow iteratively. Empty results and `org_not_found` are valid outcomes, not errors. |
| `APOLLO_PEOPLE_ENRICHMENT` | Enrich person with Apollo | Enriches and retrieves information for a person from Apollo.io. Requires one of: `id`, `email`, `hashed_email`, `linkedin_url`, or (`first_name` and `last_name` with `organization_name` or `domain`) for matching. `webhook_url` must be provided if `reveal_phone_number` is true. Name-only inputs without `organization_name` or `domain` frequently return no matches. |
| `APOLLO_PEOPLE_SEARCH` | Apollo people search | Searches Apollo's contact database for people using various filters; results capped at 50,000 records and does not enrich contact data. Combining multiple strict filters (organization_ids, person_titles, person_seniorities) can return zero results — start broad and narrow iteratively. Result records may have null email, phone, or organization fields. |
| `APOLLO_SEARCH_ACCOUNTS` | Search Apollo Accounts | Searches for accounts within your existing Apollo.io database using various criteria; requires a paid plan and is limited to 50,000 records. |
| `APOLLO_SEARCH_CALLS` | Search for Calls | Searches for call records in Apollo.io using filters like date range, duration, direction (inbound/outgoing), users, contacts, purposes, outcomes, and keywords. Supports pagination for efficient data retrieval. |
| `APOLLO_SEARCH_CONTACTS` | Search Apollo contacts | Searches Apollo contacts using keywords, stage IDs (from 'List Contact Stages' action), or sorting (max 50,000 records; `sort_ascending` requires `sort_by_field`). Search before creating contacts to avoid duplicates. |
| `APOLLO_SEARCH_NEWS_ARTICLES` | Search news articles | Tool to search for news articles about companies in Apollo's database. Use when you need to find recent news, announcements, or updates about specific organizations using their Apollo IDs. |
| `APOLLO_SEARCH_OUTREACH_EMAILS` | Search outreach emails | Tool to search for outreach emails sent through Apollo sequences. Use when you need to find emails created and sent by your team as part of Apollo email campaigns. This endpoint requires a master API key and has a display limit of 50,000 records (100 records per page, up to 500 pages). |
| `APOLLO_SEARCH_SEQUENCES` | Search sequences | Searches for sequences (e.g., automated email campaigns) in Apollo.io. |
| `APOLLO_SEARCH_TASKS` | Search tasks | Searches for tasks in Apollo.io using filters like keywords, date ranges (due, created, updated), priorities, types, assigned users, associated contacts/accounts, supporting sorting and pagination. |
| `APOLLO_UPDATE_ACCOUNT` | Update an Apollo account | Updates specified attributes of an existing account in Apollo.io. |
| `APOLLO_UPDATE_ACCOUNT_OWNERS` | Update account ownership | Updates the ownership of multiple Apollo accounts to a specified user. Use when bulk assigning account ownership to a team member. |
| `APOLLO_UPDATE_CALL_RECORD` | Update Apollo call record | Tool to update an existing call record in Apollo.io. Use when you need to modify details of a previously logged phone call such as duration, status, notes, or associated contact/account information. |
| `APOLLO_UPDATE_CONTACT` | Update Apollo contact details | Tool to update an existing contact's information in Apollo. Use when you need to modify contact details such as name, email, phone, title, organization, or custom fields. At least one field beyond contact_id must be provided. |
| `APOLLO_UPDATE_CONTACT_OWNERSHIP` | Update contact ownership | Updates the ownership of specified Apollo contacts to a given Apollo user, who must be part of the same team. |
| `APOLLO_UPDATE_CONTACTS_BULK` | Bulk update Apollo contacts | Tool to bulk update multiple Apollo contacts with a single API call. Use when updating multiple contacts simultaneously - either apply the same updates to all contacts using contact_ids, or apply different updates to each contact using contact_attributes. Automatically processes asynchronously for more than 100 contacts. |
| `APOLLO_UPDATE_CONTACT_STAGE` | Update contact stage | Updates the stage for one or more existing contacts in Apollo.io to a new valid contact stage, useful for managing sales funnel progression. |
| `APOLLO_UPDATE_CONTACT_STATUS_IN_SEQUENCE` | Update contact status in sequence | Updates a contact's status within a designated Apollo sequence, but cannot set the status to 'active'. |
| `APOLLO_UPDATE_DEALS` | Update Apollo deal | Updates specified fields of an existing Apollo.io deal (opportunity), requiring a valid `opportunity_id`. |
| `APOLLO_VIEW_API_USAGE_STATS` | View API Usage Stats | Fetches Apollo API usage statistics and rate limits for the connected team. Use before large enrichment/search runs to understand current API usage and plan/budget constraints. If experiencing 403s on credit/usage sensitive endpoints, use this tool to confirm whether the key has master privileges (this endpoint will 403 without a master key). |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Apollo MCP server is an implementation of the Model Context Protocol that connects your AI agent to Apollo. It provides structured and secure access so your agent can perform Apollo operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. 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 Apollo account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Apollo

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

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

### 4. Import modules

No description provided.
```python
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()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
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")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

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, apollo)
- 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 Apollo tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
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=["apollo"],
    )

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

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["apollo"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Apollo actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
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}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

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 Apollo
```python
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!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Apollo, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
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=["apollo"],
    )

    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 Apollo actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Apollo 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!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["apollo"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Apollo actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected Apollo to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Apollo 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 Apollo MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/apollo/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/apollo/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/apollo/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/apollo/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/apollo/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/apollo/framework/codex)
- [Cursor](https://composio.dev/toolkits/apollo/framework/cursor)
- [VS Code](https://composio.dev/toolkits/apollo/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/apollo/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/apollo/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/apollo/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/apollo/framework/cli)
- [Google ADK](https://composio.dev/toolkits/apollo/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/apollo/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/apollo/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/apollo/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/apollo/framework/crew-ai)

## Related Toolkits

- [Hubspot](https://composio.dev/toolkits/hubspot) - HubSpot is an all-in-one marketing, sales, and customer service platform. It lets teams nurture leads, automate outreach, and track every customer interaction in one place.
- [Pipedrive](https://composio.dev/toolkits/pipedrive) - Pipedrive is a sales management platform offering pipeline visualization, lead tracking, and workflow automation. It helps sales teams keep deals moving forward efficiently and never miss a follow-up.
- [Salesforce](https://composio.dev/toolkits/salesforce) - Salesforce is a leading CRM platform that helps businesses manage sales, service, and marketing. It centralizes customer data, enabling teams to drive growth and build strong relationships.
- [Attio](https://composio.dev/toolkits/attio) - Attio is a customizable CRM and workspace for managing your team's relationships and workflows. It helps teams organize contacts, automate tasks, and collaborate more efficiently.
- [Acculynx](https://composio.dev/toolkits/acculynx) - AccuLynx is a cloud-based roofing business management software for contractors. It streamlines project tracking, lead management, and document sharing.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Affinity](https://composio.dev/toolkits/affinity) - Affinity is a relationship intelligence CRM that helps private capital investors find, manage, and close more deals. It streamlines deal flow and surfaces key connections to help you win opportunities.
- [Agencyzoom](https://composio.dev/toolkits/agencyzoom) - AgencyZoom is a sales and performance platform built for P&C insurance agencies. It helps agents boost sales, retain clients, and analyze producer results in one place.
- [Bettercontact](https://composio.dev/toolkits/bettercontact) - Bettercontact is a smart contact enrichment tool for finding emails and phone numbers. It helps boost lead generation with automated, waterfall search across multiple sources.
- [Blackbaud](https://composio.dev/toolkits/blackbaud) - Blackbaud provides cloud-based software for nonprofits, schools, and healthcare institutions. It streamlines fundraising, donor management, and mission-driven operations.
- [Brilliant directories](https://composio.dev/toolkits/brilliant_directories) - Brilliant Directories is an all-in-one platform for building and managing online membership communities and business directories. It streamlines listings, member management, and engagement tools into a single, easy interface.
- [Capsule crm](https://composio.dev/toolkits/capsule_crm) - Capsule CRM is a user-friendly CRM platform for managing contacts and sales pipelines. It helps businesses organize relationships and streamline their sales process efficiently.
- [Centralstationcrm](https://composio.dev/toolkits/centralstationcrm) - CentralStationCRM is an easy-to-use CRM software focused on collaboration and long-term customer relationships. It helps teams manage contacts, deals, and communications all in one place.
- [Clientary](https://composio.dev/toolkits/clientary) - Clientary is a platform for managing clients, invoices, projects, proposals, and more. It streamlines client work and saves you serious admin time.
- [Close](https://composio.dev/toolkits/close) - Close is a CRM platform built for sales teams, combining calling, email automation, and predictive dialers. It streamlines sales workflows and boosts productivity with all-in-one communication tools.
- [Dropcontact](https://composio.dev/toolkits/dropcontact) - Dropcontact is a B2B email finder and data enrichment service for professionals. It delivers verified email addresses and enriches contact info with up-to-date data.
- [Dynamics365](https://composio.dev/toolkits/dynamics365) - Dynamics 365 is Microsoft's platform combining CRM, ERP, and productivity apps. It streamlines sales, marketing, service, and operations in one place.
- [Espocrm](https://composio.dev/toolkits/espocrm) - EspoCRM is an open-source web application for managing customer relationships. It helps businesses organize contacts, track leads, and streamline their sales process.
- [Fireberry](https://composio.dev/toolkits/fireberry) - Fireberry is a CRM platform that streamlines customer and sales management. It helps businesses organize contacts, automate sales, and integrate with other business tools.
- [Firmao](https://composio.dev/toolkits/firmao) - Firmao is a business information platform offering company, industry, and market data. Use it to quickly research firms and gain competitive market insights.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Apollo MCP?

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

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

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

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)