# How to integrate Mezmo MCP with LlamaIndex

```json
{
  "title": "How to integrate Mezmo MCP with LlamaIndex",
  "toolkit": "Mezmo",
  "toolkit_slug": "mezmo",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/mezmo/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/mezmo/framework/llama-index.md",
  "updated_at": "2026-05-12T10:18:55.352Z"
}
```

## Introduction

This guide walks you through connecting Mezmo to LlamaIndex using the Composio tool router. By the end, you'll have a working Mezmo agent that can send application error logs to mezmo, delete outdated pipeline alert for a component, ingest security event logs from last hour through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Mezmo account through Composio's Mezmo MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Mezmo with

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

The Mezmo MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, and more directly to your Mezmo account. It provides structured and secure access to your log management and telemetry pipelines, so your agent can ingest logs, manage pipeline alerts, streamline monitoring, and automate log-driven workflows on your behalf.
- Automated log ingestion: Seamlessly send structured log events from any host or service to Mezmo for real-time analysis and monitoring.
- Pipeline alert deletion: Direct your agent to remove specific alerts tied to components in your pipelines, helping manage noise and maintain alert hygiene.
- Streamlined alert management: Enable your agent to clean up outdated or redundant alerts, keeping your pipeline monitoring focused and actionable.
- Real-time telemetry processing: Let your agent push telemetry data instantly for advanced analytics, troubleshooting, and observability workflows.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `MEZMO_CREATE_CATEGORY` | Create Category | Tool to create a new category for views, boards, or screens in Mezmo. Use when organizing Mezmo resources into categories. |
| `MEZMO_CREATE_INGESTION_EXCLUSION` | Create Ingestion Exclusion Rule | Tool to create an exclusion rule for log ingestion to control costs. Use this when you need to prevent specific logs from being ingested or stored based on query patterns. Exclusion rules help reduce ingestion costs by filtering out debug logs, test environment logs, or other non-essential log data. |
| `MEZMO_CREATE_KEY` | Create API Key | Tool to create a new API key (ingestion or service key) in Mezmo. The API auto-generates a unique name for the key. Use when you need to provision a new key for log ingestion or API access. |
| `MEZMO_CREATE_MEMBER` | Create Member Invitation | Tool to invite a new member to the Mezmo organization with a specified role. Use this to send invitations to team members and optionally assign them to specific groups. |
| `MEZMO_CREATE_PRESET_ALERT` | Create Preset Alert | Tool to create a new preset alert in Mezmo with specified name and notification channels. Use this to configure alerts that can be triggered based on log conditions. Supports email, PagerDuty, and webhook notification channels. |
| `MEZMO_CREATE_VIEW` | Create View | Tool to create a new Mezmo view with filtering and alert configuration. Use when you need to set up custom log views with specific filters (query, hosts, apps, levels, tags) and optional alert channels (email, PagerDuty, webhook). At least one filter parameter must be provided in addition to the view name. |
| `MEZMO_DELETE_CATEGORY` | Delete Category | Tool to delete a category by its type and ID. Use when you need to remove a view, board, or screen category from Mezmo configuration. |
| `MEZMO_DELETE_INGESTION_EXCLUSION` | Delete Ingestion Exclusion | Tool to remove an ingestion exclusion rule by its ID. Use when you need to delete a specific exclusion rule from Mezmo's ingestion configuration. |
| `MEZMO_DELETE_KEY` | Delete API Key | Tool to delete an API key by its unique identifier. Use when you need to remove an ingestion key from Mezmo to revoke access. |
| `MEZMO_DELETE_MEMBER` | Delete Organization Member | Tool to remove a member from the organization by their email address. Use when you need to revoke a user's access to the organization. |
| `MEZMO_DELETE_PIPELINE_ALERT` | Delete Pipeline Alert | Tool to delete an alert for a specific component within a pipeline. Use after confirming pipeline ID, component kind, component ID, and alert ID. |
| `MEZMO_DELETE_PRESET_ALERT` | Delete Preset Alert | Tool to delete a preset alert by its ID. Use after confirming the preset alert ID exists. |
| `MEZMO_DELETE_VIEW` | Delete View | Tool to delete a view by its ID. Use when you need to remove a specific view from Mezmo. |
| `MEZMO_GET_ALERT` | Get Preset Alert | Tool to retrieve details of a specific preset alert by its ID. Use when you need to view the configuration of an existing alert. |
| `MEZMO_GET_CATEGORY` | Get Category | Tool to retrieve a category configuration by its type and ID. Use when you need to fetch details about a specific Mezmo category (view, board, or screen). |
| `MEZMO_GET_INDEX_RATE_ALERT` | Get Index Rate Alert Configuration | Tool to retrieve current index rate alert settings for the Mezmo account. Use this to check if index rate alerting is enabled and view configured thresholds and notification channels. |
| `MEZMO_GET_INGESTION_EXCLUSION` | Get Ingestion Exclusion Rule | Tool to retrieve an ingestion exclusion rule by its ID. Use when you need to fetch details of a specific exclusion rule. |
| `MEZMO_GET_INGESTION_STATUS` | Get Ingestion Status | Tool to get the current ingestion status for the Mezmo account. Use when you need to check whether log ingestion is currently active or paused. |
| `MEZMO_GET_KEY` | Get API Key | Tool to retrieve an API key configuration by its ID. Use when you need to fetch details about a specific Mezmo API key. |
| `MEZMO_GET_MEMBER` | Get Member | Tool to retrieve member information by their ID. Use when you need to fetch details about a specific member in your Mezmo account. |
| `MEZMO_GET_STREAM_CONFIG` | Get Stream Configuration | Tool to retrieve the current event streaming configuration for the Mezmo account. Use when you need to check if streaming is enabled and get streaming settings. Returns error details if streaming is unavailable on the account/plan. |
| `MEZMO_GET_VIEW` | Get View Details | Tool to retrieve details of a specific view by its ID. Use when you need to fetch view configuration including name, query, filters, and other attributes. |
| `MEZMO_INGEST_LOGS` | Ingest Logs to Mezmo | Ingest log lines into Mezmo Log Analysis. Use this tool to send structured log data from hosts, applications, or services to Mezmo for centralized logging, analysis, and alerting. Logs are sent to the Mezmo ingestion endpoint and will appear in the Mezmo dashboard. |
| `MEZMO_LIST_ALERTS` | List Preset Alerts | Tool to list all preset alerts configured for the Mezmo account. Use when you need to retrieve notification rules that trigger based on log patterns. Returns preset alert configurations including their channels (email, PagerDuty, webhook). |
| `MEZMO_LIST_KEYS` | List API Keys | Tool to list all API keys and ingestion keys configured for the account. Use when you need to retrieve all keys for viewing or management purposes. |
| `MEZMO_LIST_MEMBERS` | List Members | Tool to list all team members in the Mezmo account configuration. Use when you need to retrieve information about all members in the organization. |
| `MEZMO_LIST_PIPELINES` | List Telemetry Pipelines | Tool to list all telemetry pipelines configured for the account. Use when you need to view or retrieve information about existing pipelines that manage the flow and transformation of telemetry data. |
| `MEZMO_LIST_VIEWS` | List Views | Tool to list all views configured for the account. Views are saved search queries and filters for quick access to specific log data. |
| `MEZMO_RESUME_INGESTION` | Resume Log Ingestion | Tool to resume log ingestion for the account after it has been stopped. Use when you need to re-enable log collection after a pause. |
| `MEZMO_UPDATE_CATEGORY` | Update Category | Tool to update a category name by its type and ID. Use when you need to rename an existing category in Mezmo. |
| `MEZMO_UPDATE_INDEX_RATE_ALERT` | Update Index Rate Alert Configuration | Tool to configure index rate alerting settings including thresholds and notification channels. Use this when you need to set up or modify alerts for unusual log ingestion rates based on absolute line counts or statistical deviations. |
| `MEZMO_UPDATE_INGESTION_EXCLUSION` | Update Ingestion Exclusion Rule | Tool to update an existing exclusion rule by its ID. Use when you need to modify the query, active status, indexonly behavior, or title of an existing exclusion rule. At least one field (query, active, indexonly, or title) must be provided for update. |
| `MEZMO_UPDATE_KEY` | Update API Key | Tool to update an API key name by its ID. Use when you need to rename an existing Mezmo API key. |
| `MEZMO_UPDATE_MEMBER` | Update Member Role and Groups | Tool to update a member's role and group assignments by their email address. Use when you need to change a member's permissions or group memberships. |
| `MEZMO_UPDATE_PRESET_ALERT` | Update Preset Alert | Tool to update an existing preset alert by ID. Allows modifying the alert's name and notification channels. Use when you need to change alert configuration after creation. Requires full resource representation with both name and channels. |
| `MEZMO_UPDATE_VIEW` | Update Mezmo View | Tool to update an existing Mezmo view by its ID. Use when you need to modify a view's name or search query. |

## Supported Triggers

None listed.

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

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

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

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 Mezmo 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, mezmo)
- 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 Mezmo 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=["mezmo"],
    )

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

  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 Mezmo 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 Mezmo
```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 Mezmo, 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=["mezmo"],
    )

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

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

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

## Related Toolkits

- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.
- [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.
- [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.
- [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses.
- [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure.
- [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure.
- [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction.
- [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting.
- [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache.
- [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence.
- [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place.
- [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines.
- [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure.
- [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code.
- [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows.
- [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights.
- [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews.
- [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease.
- [Blocknative](https://composio.dev/toolkits/blocknative) - Blocknative delivers real-time mempool monitoring and transaction management for public blockchains. Instantly track pending transactions and optimize blockchain interactions with live data.

## Frequently Asked Questions

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

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

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

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

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