# How to integrate Lemlist MCP with LlamaIndex

```json
{
  "title": "How to integrate Lemlist MCP with LlamaIndex",
  "toolkit": "Lemlist",
  "toolkit_slug": "lemlist",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/lemlist/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/lemlist/framework/llama-index.md",
  "updated_at": "2026-05-12T10:17:22.635Z"
}
```

## Introduction

This guide walks you through connecting Lemlist to LlamaIndex using the Composio tool router. By the end, you'll have a working Lemlist agent that can export all leads from current campaign, download list of unsubscribed emails, unsubscribe specific lead from a campaign through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Lemlist account through Composio's Lemlist MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Lemlist with

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

The Lemlist MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Lemlist account. It provides structured and secure access to your outreach campaigns, so your agent can manage leads, automate campaign exports, monitor unsubscribe lists, and orchestrate multichannel engagement on your behalf.
- Automated campaign management: Retrieve campaign details by ID, audit campaign sequences, and start or monitor campaign exports for streamlined reporting and analytics.
- Lead and subscriber control: Unsubscribe leads from campaigns, delete unsubscribed emails, or export detailed lists of campaign leads to keep your outreach data fresh and compliant.
- Outreach data exports: Initiate and track asynchronous exports of campaign statistics or download CSVs of unsubscribed contacts for deeper insights and record-keeping.
- Webhook administration: Fetch all configured webhooks to sync Lemlist with your other tools or audit integration points for better workflow automation.
- Schedule management: Permanently delete schedules you no longer need, ensuring your campaigns stay organized and up to date.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `LEMLIST_CREATE_COMPANY_NOTE` | Create Company Note | Tool to create a note attached to a specific company. Use when you need to add annotations or notes to a company record for tracking purposes. |
| `LEMLIST_DELETE_DELETE_SCHEDULE` | Delete Schedule | Tool to delete a specific schedule by scheduleId. Use when you need to remove a schedule permanently after confirming its ID. |
| `LEMLIST_DELETE_DELETE_UNSUBSCRIBE_EMAIL` | Delete Unsubscribed Email | Tool to delete an email from the unsubscribed list. Use when restoring a subscriber who has opted back in and you need to remove them from the suppressed contacts. |
| `LEMLIST_DELETE_UNSUBSCRIBE_LEAD_FROM_CAMPAIGN` | Unsubscribe Lead From Campaign | Tool to unsubscribe a lead from a campaign. Use when you need to stop further outreach by removing a lead from the specified campaign. |
| `LEMLIST_GET_ALL_WEBHOOKS` | Get All Webhooks | Tool to retrieve the list of all webhooks configured for the team. Use when you need to sync or audit active webhooks. |
| `LEMLIST_GET_CAMPAIGN_BY_ID` | Get Campaign By ID | Tool to retrieve a specific campaign by campaignId. Use when you need detailed campaign information by ID. |
| `LEMLIST_GET_CAMPAIGN_EXPORT_START` | Start Campaign Export | Tool to start an asynchronous export of all campaign statistics (CSV). Use when you need to initiate a CSV export for a given campaign and track its progress. |
| `LEMLIST_GET_CAMPAIGN_EXPORT_STATUS` | Get Campaign Export Status | Tool to check the status of an asynchronous campaign export. Use after starting an export to poll until done or error. |
| `LEMLIST_GET_CAMPAIGN_SEQUENCES` | Get Campaign Sequences | Tool to retrieve a list of all sequences for a campaign with steps and conditions. Use after fetching campaign to inspect its nested sequences and branching rules. |
| `LEMLIST_GET_CAMPAIGN_STATS` | Get Campaign Stats | Tool to retrieve performance statistics for a specific campaign within a date range. Use when you need campaign analytics including lead engagement, message delivery, and step-by-step performance metrics. |
| `LEMLIST_GET_COMPANIES_SCHEMA` | Get Companies Schema | Tool to retrieve the schema definition for companies in the people database. Use when you need to understand the structure, fields, and data types available for company records. |
| `LEMLIST_GET_CONTACT_MESSAGES` | Get Contact Messages | Tool to retrieve all messages exchanged with a specific contact. Use when you need to fetch conversation history for a contact by their contactId. |
| `LEMLIST_GET_DATABASE_FILTERS` | Get Database Filters | Tool to retrieve available filters for searching the people and companies database. Use when you need to discover what search criteria are available before querying the database. |
| `LEMLIST_GET_EXPORT_CAMPAIGN_LEADS` | Export Campaign Leads | Tool to export campaign leads with state filtering and choose between JSON or CSV output. Use when you need to download leads and their statuses for reporting or analysis. |
| `LEMLIST_GET_EXPORT_UNSUBSCRIBES` | Export Unsubscribes | Tool to download a CSV file containing all unsubscribed email addresses. Use when you need to export the full unsubscribes list for analysis or archival. |
| `LEMLIST_GET_GET_UNSUBSCRIBE_EMAIL` | Get Unsubscribed Email | Tool to retrieve a single unsubscribed email record. Use when you need to verify if a specific email has opted out of campaigns before re-subscribing them. |
| `LEMLIST_GET_LABEL` | Get Label | Tool to retrieve information about a specific label by its ID. Use when you need details about an inbox label. |
| `LEMLIST_GET_LIST_CAMPAIGNS` | List Campaigns | Tool to retrieve a list of campaigns for the team. Use when you need to discover campaign IDs, names, or statuses before performing operations like auditing or pausing campaigns. |
| `LEMLIST_GET_LIST_TASKS` | List Tasks | Tool to retrieve all pending tasks assigned to team members. Use when you need to view tasks by campaign, assignee, or other filters. Completed tasks are automatically excluded from results. |
| `LEMLIST_GET_LIST_TEAM_SENDERS` | List Team Senders | Tool to retrieve all team members and their associated campaigns. Use when you need to discover which team members are managing which campaigns or to understand campaign distribution across the team. |
| `LEMLIST_GET_LIST_WATCHLIST_SIGNALS` | List Watchlist Signals | Tool to retrieve paginated watchlist signals with filtering and sorting. Use when you need to fetch signals from watchlists based on type, status, date range, or specific watchlist ID. |
| `LEMLIST_GET_PEOPLE_SCHEMA` | Get People Schema | Tool to retrieve the schema definition for people in the people database. Use when you need to understand available fields and their structure before querying or importing people data. |
| `LEMLIST_GET_RETRIEVE_ACTIVITIES` | Retrieve Activities | Tool to fetch recent campaign activities. Use after authentication to retrieve activities filtered by campaignId, type, or limit. |
| `LEMLIST_GET_RETRIEVE_LEAD_BY_EMAIL` | Retrieve Lead By Email | Tool to retrieve a lead by their email address. Use when you have a lead's email to fetch complete lead details. |
| `LEMLIST_GET_RETRIEVE_UNSUBSCRIBES` | Retrieve Unsubscribes | Tool to retrieve the list of all people who are unsubscribed. Use when you need to sync or audit unsubscribed contacts across your campaigns. |
| `LEMLIST_GET_TEAM_CREDITS` | Get Team Credits | Tool to retrieve credits left in the team. Use after authenticating your session. |
| `LEMLIST_GET_TEAM_INFO` | Get Team Info | Tool to retrieve information about your team. Use after authentication to inspect current team settings, members, webhooks, and enabled features. Verify the returned teamId matches the intended workspace before passing it to campaign-creation or other write operations to avoid creating resources in the wrong account context. |
| `LEMLIST_GET_USER` | Get User | Tool to retrieve all information for a specific user by their ID. Use when you have a user ID to fetch complete user details including LinkedIn settings and connected mailboxes. |
| `LEMLIST_GET_USER_INFO` | Get User Info | Tool to retrieve all information of the authenticated user. Use after confirming a valid access token. |
| `LEMLIST_LIST_COMPANIES` | List Companies | Tool to retrieve a paginated list of all companies in your CRM. Use when you need to discover companies, search by name, or fetch company details for further operations. |
| `LEMLIST_LIST_COMPANY_NOTES` | List Company Notes | Tool to retrieve all notes associated with a specific company. Use when you need to view annotations, comments, or activities logged against a company record. |
| `LEMLIST_LIST_LABELS` | List Labels | Tool to list all labels available to your team. Use when you need to retrieve the full list of labels for inbox organization or filtering. |
| `LEMLIST_PATCH_MARK_LEAD_AS_NOT_INTERESTED_IN_CAMPAIGN` | Mark Lead as Not Interested in Campaign | Tool to mark a lead as not interested in a specific campaign. Use after confirming campaign and lead IDs to set status to not_interested. |
| `LEMLIST_PATCH_UPDATE_CAMPAIGN` | Update Campaign | Tool to update settings of a campaign. Use after fetching or creating a campaign to adjust name, stop-on behaviors, and other campaign flags. |
| `LEMLIST_PATCH_UPDATE_SCHEDULE` | Update Schedule | Tool to update an existing schedule with new parameters. Use after retrieving schedule details to adjust days, time window, and limits. |
| `LEMLIST_PATCH_UPDATE_SEQUENCE_STEP` | Update Sequence Step | Tool to update an existing step in a sequence (edit subject/message/delay/etc.) by sequenceId and stepId. Use after retrieving sequences to modify step content or timing. |
| `LEMLIST_POST_ADD_STEP_TO_SEQUENCE` | Add Step to Sequence | Tool to add a new step (email, LinkedIn, conditional, etc.) to an existing sequence. Use when building or editing campaign sequences to add outreach steps. |
| `LEMLIST_POST_ADD_UNSUBSCRIBE_EMAIL_DOMAIN` | Add Unsubscribe Email/Domain | Tool to add an email or domain to the unsubscribed list. Use when you need to globally block sending to a specific recipient or domain. |
| `LEMLIST_POST_ADD_VARIABLES_TO_LEAD` | Add Variables to Lead | Tool to add one or more variables to a lead. Use when you need to enrich a lead with custom data after its creation or retrieval. |
| `LEMLIST_POST_ASSOCIATE_SCHEDULE_WITH_CAMPAIGN` | Associate schedule with campaign | Tool to associate a schedule with a campaign. Use after confirming both campaignId and scheduleId to bind a schedule to its campaign. |
| `LEMLIST_POST_CREATE_CAMPAIGN` | Create Campaign | Tool to create a new campaign. Use after confirming the team ID. Returns campaign, sequence, and schedule IDs nested under a `data` key (e.g., `result['data']['campaignId']`). |
| `LEMLIST_POST_CREATE_LABEL` | Create Label | Tool to create a new label for inbox conversations. Use when you need to organize inbox messages with custom labels. |
| `LEMLIST_POST_CREATE_LEAD_IN_CAMPAIGN` | Create Lead In Campaign | Tool to create a lead and add it to a specific campaign. Use when you need to enroll a new lead into an outreach campaign. Supports optional deduplication and enrichment features. |
| `LEMLIST_POST_CREATE_SCHEDULE` | Create Schedule | Tool to create a new schedule for the team. Use when you need to define custom active times or delays for outreach operations. Returns a `scheduleId`; store it for association with campaigns or sequences. Avoid creating unused schedules. |
| `LEMLIST_POST_CREATE_TASK` | Create Task | Tool to create a manual task (opportunity) associated with a contact, company, or lead. Use when you need to track follow-ups or action items for outreach prospects. |
| `LEMLIST_POST_IGNORE_TASKS` | Ignore Tasks | Tool to mark one or more tasks as ignored in Lemlist. Use when you want to dismiss tasks without completing them. |
| `LEMLIST_POST_MARK_LEAD_AS_INTERESTED` | Mark Lead As Interested | Tool to mark a lead as interested in all campaigns. Use when a lead responds positively and you want to advance or personalize your outreach. |
| `LEMLIST_POST_MARK_LEAD_AS_INTERESTED_IN_CAMPAIGN` | Mark Lead As Interested In Campaign | Tool to mark a lead as interested in a specific campaign. Use after confirming the lead's positive engagement in that campaign. |
| `LEMLIST_POST_MARK_LEAD_AS_NOT_INTERESTED` | Mark Lead As Not Interested | Tool to mark a lead as not interested in all campaigns. Use when a lead explicitly declines outreach and should be paused across campaigns. |
| `LEMLIST_POST_PAUSE_CAMPAIGN` | Pause a running campaign | Tool to pause a running campaign. Use after confirming you have the correct campaign ID and that the campaign is currently running. |
| `LEMLIST_POST_PAUSE_LEAD` | Pause Lead | Tool to pause a lead in all campaigns or a specific campaign. Use when you want to temporarily halt outreach to a lead. |
| `LEMLIST_SEARCH_COMPANIES_DATABASE` | Search Companies Database | Tool to search the companies database using filters, keywords, and pagination. Use when you need to find companies based on criteria like industry, size, or keywords. Returns a paginated list of companies matching the specified filters. |
| `LEMLIST_SEARCH_PEOPLE_DATABASE` | Search People Database | Tool to search the Lemlist people database using filters, keywords, and pagination. Use when you need to find prospects based on criteria like location, job title, seniority, or company. Supports free-text search and structured filtering. |
| `LEMLIST_UPDATE_TASK` | Update Task | Tool to update an existing task including assignment, scheduling, and status. Use when modifying task details such as title, priority, due date, or completion status. |

## Supported Triggers

None listed.

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

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

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

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 Lemlist 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, lemlist)
- 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 Lemlist 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=["lemlist"],
    )

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

  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 Lemlist 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 Lemlist
```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 Lemlist, 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=["lemlist"],
    )

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

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

- [OpenAI Agents SDK](https://composio.dev/toolkits/lemlist/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/lemlist/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/lemlist/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/lemlist/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/lemlist/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/lemlist/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/lemlist/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/lemlist/framework/cli)
- [Google ADK](https://composio.dev/toolkits/lemlist/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/lemlist/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/lemlist/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/lemlist/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/lemlist/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.
- [Callingly](https://composio.dev/toolkits/callingly) - Callingly is a lead response management platform that automates immediate call and text follow-ups with new leads. It helps sales teams boost response speed and close more deals by connecting seamlessly with CRMs and lead sources.
- [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.

## Frequently Asked Questions

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

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

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

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

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