# How to integrate Callingly MCP with LlamaIndex

```json
{
  "title": "How to integrate Callingly MCP with LlamaIndex",
  "toolkit": "Callingly",
  "toolkit_slug": "callingly",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/callingly/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/callingly/framework/llama-index.md",
  "updated_at": "2026-05-12T10:04:52.223Z"
}
```

## Introduction

This guide walks you through connecting Callingly to LlamaIndex using the Composio tool router. By the end, you'll have a working Callingly agent that can activate a client account for onboarding, create an outbound call to new lead, get agent schedule for next week through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Callingly account through Composio's Callingly MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Callingly with

- [OpenAI Agents SDK](https://composio.dev/toolkits/callingly/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/callingly/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/callingly/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/callingly/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/callingly/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/callingly/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/callingly/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/callingly/framework/cli)
- [Google ADK](https://composio.dev/toolkits/callingly/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/callingly/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/callingly/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/callingly/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/callingly/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 Callingly
- Connect LlamaIndex to the Callingly MCP server
- Build a Callingly-powered agent using LlamaIndex
- Interact with Callingly 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 Callingly MCP server, and what's possible with it?

The Callingly MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Callingly account. It provides structured and secure access to your Callingly environment, so your agent can automate lead follow-ups, manage agents and clients, trigger outbound calls, and keep your sales workflows moving without manual intervention.
- Automated outbound call creation: Instantly generate outbound call records so your team can respond to new leads within seconds without lifting a finger.
- Agent and team management: Let your agent create, delete, or update agents and teams as your sales organization changes and grows.
- Client onboarding and offboarding: Seamlessly add, activate, deactivate, or remove client accounts as your business requires—no more manual data entry.
- Real-time webhook setup: Set up and delete webhooks to receive instant notifications for specific call or lead events, keeping your CRM and other tools in sync.
- Availability and scheduling insights: Retrieve agent schedules to optimize call assignments and guarantee leads get connected when agents are actually available.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `CALLINGLY_ACTIVATE_DEACTIVATE_CLIENT` | Activate/Deactivate Client Account | Tool to activate or deactivate a client account. Use when you need to toggle client access after onboarding or offboarding. Example: "Activate client 123" or "Deactivate client 456". |
| `CALLINGLY_CREATE_AGENT` | Create Agent | Tool to create a new agent. Use when you need to register an agent in Callingly after gathering their account ID and contact details. |
| `CALLINGLY_CREATE_CALL` | Create Outbound Call | Creates a new outbound call record and initiates a real outbound call, which incurs cost — ensure explicit user authorization and compliance with applicable consent and telemarketing regulations before use. The call will be routed to available agents on the specified team based on account-level routing configuration. Use List Teams first to get valid account_id and team_id values. Returns a call_id that can be used with Get Call to retrieve call status, recordings, and other details. |
| `CALLINGLY_CREATE_CLIENT` | Create Client | Creates a new client account in Callingly. Clients are sub-accounts under your agency account that can have their own teams, agents, and billing. Use this when onboarding a new business customer to your Callingly agency. |
| `CALLINGLY_CREATE_TEAM` | Create Team | Tool to create a new team. Use when setting up a team configuration before adding agents. |
| `CALLINGLY_CREATE_WEBHOOK` | Create Webhook | Tool to create a new webhook for call or lead events. Use when you need to receive real-time notifications on specific events. Example: "Create a webhook for call_completed events to http://example.com/callback". |
| `CALLINGLY_DELETE_AGENT` | Delete Agent | Permanently delete an agent from a Callingly account. Use when removing an agent who should no longer receive calls. Requires both the agent ID and the account ID the agent belongs to. |
| `CALLINGLY_DELETE_CLIENT` | Delete Client | Tool to delete a client. Use when you need to remove an existing client from your account after confirming its ID. |
| `CALLINGLY_DELETE_LEAD` | Delete Lead | Tool to delete a lead by ID. Use when you need to permanently remove a lead from your account after confirming its ID. Returns a success confirmation. |
| `CALLINGLY_DELETE_WEBHOOK` | Delete Webhook | Tool to delete a webhook. Use when permanently removing a webhook by its ID. |
| `CALLINGLY_GET_AGENT_SCHEDULE` | Get Agent Schedule | Tool to retrieve the availability schedule for a specific agent. Use when you need to know which days and times the agent is available. |
| `CALLINGLY_GET_CALL` | Get Call | Retrieves detailed information about a specific call by its unique ID. Returns comprehensive call metadata including status, duration, lead information, agent details, recording URLs, transcripts, and AI-generated insights. Use the LIST_CALLS action first to obtain valid call IDs. |
| `CALLINGLY_GET_LEAD` | Get Lead | Tool to retrieve details of a specific lead by its ID. Use when you need full lead details before follow-up actions. |
| `CALLINGLY_GET_TEAM` | Get Team | Tool to retrieve details of a specific team. Use after obtaining the team ID to fetch its configuration details. |
| `CALLINGLY_GET_WEBHOOK` | Get Webhook | Tool to retrieve details of a specific webhook by its ID. Use when you need to inspect a webhook's configuration before modifying or deleting it. |
| `CALLINGLY_LIST_CALLS` | List Calls | Tool to list calls. Use when you need to retrieve multiple call records with optional filters such as date range, team, and pagination after identifying the need for a collection of calls. |
| `CALLINGLY_LIST_CLIENTS` | List Clients | Tool to list clients. Use when you need to retrieve all clients associated with your account. |
| `CALLINGLY_LIST_LEADS` | List Leads | Tool to list leads based on provided filters like date range or phone number. Use after confirming filter criteria when bulk lead retrieval is needed. |
| `CALLINGLY_LIST_TEAMS` | List Teams | Tool to list teams. Use when you need to retrieve all teams associated with your account. |
| `CALLINGLY_LIST_TEAM_USERS` | List Team Users | Retrieve all agents assigned to a specific team in Callingly. Returns each agent's ID, name, priority, call cap, and any custom/integration identifiers. Use this to audit team composition or before performing agent management operations like updates or removals. |
| `CALLINGLY_LIST_USERS` | List Users | Tool to retrieve a list of agents. Use when you need to see all agents available under the authenticated account, optionally filtering by a specific client account. |
| `CALLINGLY_LIST_WEBHOOKS` | List Webhooks | Tool to list configured webhooks. Use when you need to retrieve all webhooks configured in your account to review or manage them. |
| `CALLINGLY_REMOVE_TEAM_AGENT` | Remove Team Agent | Tool to remove a specific agent from a team. Use when you need to disassociate an agent from a team after confirming both team and agent IDs. |
| `CALLINGLY_UPDATE_AGENT` | Update Agent | Tool to update an existing agent's details. Use when you need to modify agent information post-creation. |
| `CALLINGLY_UPDATE_LEAD` | Update Lead | Tool to update an existing lead's information. Use when you need to modify lead contact details, status, or blocking settings. |
| `CALLINGLY_UPDATE_SCHEDULE` | Update Agent Schedule | Tool to update an agent's availability schedule. Use when you need to set or override an agent's daily availability times. |
| `CALLINGLY_UPDATE_TEAM_AGENT_SETTINGS` | Update Team Agent Settings | Tool to update settings (priority, capacity) for a specific team agent. Use when adjusting an agent's priority or call capacity after team configuration. |
| `CALLINGLY_UPDATE_TEAM_USERS` | Update Team Users | Updates the list of agents assigned to a team. This operation replaces all existing agent assignments - any agents not included in the list will be removed from the team. Use CALLINGLY_LIST_TEAM_USERS to check current assignments before updating. |
| `CALLINGLY_UPDATE_WEBHOOK` | Update Webhook | Updates an existing webhook's configuration by ID. Supports partial updates - only provide fields you want to change. Note: When updating event-specific fields (call_status, call_lead_status, field, filter), you must also include the event field in your request. |

## Supported Triggers

None listed.

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

The Callingly MCP server is an implementation of the Model Context Protocol that connects your AI agent to Callingly. It provides structured and secure access so your agent can perform Callingly 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 Callingly account and project
- Basic familiarity with async Python/Typescript

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

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 Callingly 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, callingly)
- 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 Callingly 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=["callingly"],
    )

    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 Callingly actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Callingly 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: ["callingly"],
    },
  );

  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 Callingly 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 Callingly
```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 Callingly, 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=["callingly"],
    )

    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 Callingly actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Callingly 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: ["callingly"],
    },
  );

  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 Callingly 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 Callingly to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Callingly 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 Callingly MCP Agent with another framework

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

## Related Toolkits

- [Aeroleads](https://composio.dev/toolkits/aeroleads) - Aeroleads is a B2B lead generation platform for finding business emails and phone numbers. Grow your sales pipeline faster with powerful prospecting tools.
- [Autobound](https://composio.dev/toolkits/autobound) - Autobound is an AI-powered sales engagement platform that crafts hyper-personalized outreach and insights. It helps sales teams boost response rates and close more deals through tailored content and recommendations.
- [Better proposals](https://composio.dev/toolkits/better_proposals) - Better Proposals is a web-based tool for crafting and sending professional proposals. It helps teams impress clients and close deals faster with slick, easy-to-use templates.
- [Bidsketch](https://composio.dev/toolkits/bidsketch) - Bidsketch is a proposal software that helps businesses create professional proposals quickly and efficiently. It streamlines the proposal process, saving time while boosting client win rates.
- [Bolna](https://composio.dev/toolkits/bolna) - Bolna is an AI platform for building conversational voice agents. It helps businesses automate support and streamline interactions through natural, voice-powered conversations.
- [Botsonic](https://composio.dev/toolkits/botsonic) - Botsonic is a no-code AI chatbot builder for easily creating and deploying chatbots to your website. It empowers businesses to offer conversational experiences without writing code.
- [Botstar](https://composio.dev/toolkits/botstar) - BotStar is a comprehensive chatbot platform for designing, developing, and training chatbots visually on Messenger and websites. It helps businesses automate conversations and customer interactions without coding.
- [Callerapi](https://composio.dev/toolkits/callerapi) - CallerAPI is a white-label caller identification platform for branded caller ID and fraud prevention. It helps businesses boost customer trust while stopping spam, fraud, and robocalls.
- [Callpage](https://composio.dev/toolkits/callpage) - Callpage is a lead capture platform that lets businesses instantly connect with website visitors via callback. It boosts lead generation and increases your sales conversion rates.
- [Clearout](https://composio.dev/toolkits/clearout) - Clearout is an AI-powered service for verifying, finding, and enriching email addresses. It boosts deliverability and helps you discover high-quality leads effortlessly.
- [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.
- [Convolo ai](https://composio.dev/toolkits/convolo_ai) - Convolo ai is an AI-powered communications platform for sales teams. It accelerates lead response and improves conversion rates by automating calls and integrating workflows.
- [Delighted](https://composio.dev/toolkits/delighted) - Delighted is a customer feedback platform based on the Net Promoter System®. It helps you quickly gather, track, and act on customer sentiment.
- [Docsbot ai](https://composio.dev/toolkits/docsbot_ai) - Docsbot ai is a platform that lets you build custom AI chatbots trained on your documentation. It automates customer support and content generation, saving time and improving response quality.
- [Emelia](https://composio.dev/toolkits/emelia) - Emelia is an all-in-one B2B prospecting platform for cold-email, LinkedIn outreach, and prospect research. It streamlines outbound campaigns so you can find, engage, and warm up leads faster.
- [Findymail](https://composio.dev/toolkits/findymail) - Findymail is a B2B data provider offering verified email and phone contacts for sales prospecting. Enhance outreach with automated exports, email verification, and CRM enrichment.
- [Freshdesk](https://composio.dev/toolkits/freshdesk) - Freshdesk is customer support software with ticketing and automation tools. It helps teams streamline helpdesk operations for faster, better customer support.
- [Fullenrich](https://composio.dev/toolkits/fullenrich) - FullEnrich is a B2B contact enrichment platform that aggregates emails and phone numbers from 15+ data vendors. Instantly find and verify lead contact data to boost your outreach.
- [Gatherup](https://composio.dev/toolkits/gatherup) - GatherUp is a customer feedback and online review management platform. It helps businesses boost their reputation by streamlining how they collect and manage customer feedback.
- [Getprospect](https://composio.dev/toolkits/getprospect) - Getprospect is a business email discovery tool with LinkedIn integration. Use it to quickly find and verify professional email addresses.

## Frequently Asked Questions

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

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

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

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

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