# How to integrate RedCircle API MCP with LlamaIndex

```json
{
  "title": "How to integrate RedCircle API MCP with LlamaIndex",
  "toolkit": "RedCircle API",
  "toolkit_slug": "redcircle_api",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/redcircle_api/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/redcircle_api/framework/llama-index.md",
  "updated_at": "2026-03-29T06:47:27.715Z"
}
```

## Introduction

This guide walks you through connecting RedCircle API to LlamaIndex using the Composio tool router. By the end, you'll have a working RedCircle API agent that can search target for nintendo switch bundles, get reviews for dyson vacuums at target, list top-rated target products in electronics through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a RedCircle API account through Composio's RedCircle API MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate RedCircle API with

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

The RedCircle API MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your RedCircle API account. It provides structured and secure access so your agent can perform RedCircle API operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `REDCIRCLE_API_ADD_ZIPCODES` | Add Zipcodes | Tool to add zipcodes to your RedCircle API account for geolocation targeting. Use when you need to localize product searches by specific postal codes. New zipcodes take approximately 2 minutes to become available after being added. |
| `REDCIRCLE_API_CLEAR_COLLECTION_REQUESTS` | Clear Collection Requests | Tool to remove all requests from a specified collection. Collections can only be cleared when not actively running. Use when you need to empty a collection of all its requests. |
| `REDCIRCLE_API_CREATE_COLLECTION` | Create Collection | Tool to create a new collection for running up to 15,000 requests on a schedule. Use when you need to organize and schedule batch requests with various scheduling patterns, priority levels, and notification methods. |
| `REDCIRCLE_API_CREATE_DESTINATION` | Create Destination | Tool to create a new destination for uploading Collection Result Sets to cloud storage. Use when you need to configure a storage destination for result sets with providers like S3, GCS, Azure, OSS, or S3-compatible storage. |
| `REDCIRCLE_API_CREATE_REQUESTS` | Create Requests | Tool to add up to 1,000 requests to an existing collection. Use when you need to populate a collection with product requests. Collections have a maximum of 15,000 requests (100 if include_html=true). Sequential calls required; parallel requests trigger HTTP 429 errors. |
| `REDCIRCLE_API_DELETE_COLLECTION` | Delete Collection | Tool to remove a collection from the system by ID. Use when you need to delete a collection that is not currently running. |
| `REDCIRCLE_API_DELETE_DESTINATION` | Delete Destination | Tool to remove a destination from your RedCircle API account. Use when you need to permanently delete a specific destination by its ID. |
| `REDCIRCLE_API_DELETE_REQUEST_FROM_COLLECTION` | Delete Request from Collection | Tool to remove an individual request from a collection. Use when you need to delete a specific request from a collection by providing both collection_id and request_id. Collections must not be running during deletion. |
| `REDCIRCLE_API_DELETE_REQUESTS_IN_BULK` | Delete Requests In Bulk | Tool to delete multiple requests from a collection in bulk. Use when you need to remove multiple requests efficiently. Note: Requests can only be deleted when the collection is not running. |
| `REDCIRCLE_API_DELETE_ZIPCODES` | Delete Zipcodes | Tool to remove zipcodes from your RedCircle API account. Use when you need to delete specific zipcode/domain pairs from your account. |
| `REDCIRCLE_API_GET_ACCOUNT_INFORMATION` | Get Account Information | Tool to retrieve account information, usage metrics, and platform status. Use when you need to check account credits, limits, plan details, or platform component status. |
| `REDCIRCLE_API_GET_COLLECTION` | Get Collection | Tool to retrieve complete information about a specific collection. Use when you need detailed collection metadata including status, schedule, and configuration. |
| `REDCIRCLE_API_GET_REQUESTS_CSV_LINKS` | Get Requests CSV Links | Tool to retrieve CSV download links for all requests in a collection. Use when you need to export request data in CSV format. Each CSV file contains up to 1000 requests. |
| `REDCIRCLE_API_GET_REQUESTS_JSON_LINKS` | Get Requests JSON Links | Tool to retrieve download links for all requests in a collection in JSON format. Use when you need to access request data from a specific collection. Returns paginated URLs for downloading request information. |
| `REDCIRCLE_API_GET_RESULT_SET_CSV` | Get Result Set CSV | Tool to retrieve a result set in CSV format with optional field filtering. Use when you need to export processed results from a collection as CSV files. Supports field selection using dot notation for nested fields. Results maintain 14-day retention. |
| `REDCIRCLE_API_GET_RESULT_SET_JSON` | Get Result Set JSON | Tool to retrieve a result set in JSON format with download links. Use when you need to access processed results from a specific collection and result set. Returns detailed result information including download URLs for data files. |
| `REDCIRCLE_API_GET_RESULT_SET_JSON_LINES` | Get Result Set JSON Lines | Tool to retrieve a result set in JSON Lines format with download links. Use when you need to access processed results as newline-delimited JSON files. JSON Lines format provides one valid JSON object per line, ideal for streaming and processing large datasets. |
| `REDCIRCLE_API_GET_TARGET_PRODUCT_DATA` | Get Target Product Data | Tool to retrieve Target data in real-time including search results, product information, reviews, or category listings. Use when you need to access Target.com product data such as searching for products, getting specific product details, retrieving reviews, or listing categories. |
| `REDCIRCLE_API_LIST_CATEGORIES` | List Categories | Tool to retrieve all top-level (root) categories or filter results using optional parameters. Use when you need to browse the category hierarchy, search for specific categories, or retrieve category details. Parameters id, parent_id, and search_term are mutually exclusive. |
| `REDCIRCLE_API_LIST_COLLECTIONS` | List Collections | Tool to retrieve all collections configured on your RedCircle API account with filtering and pagination. Use when you need to browse collections, filter by status or search term, or manage collection metadata. |
| `REDCIRCLE_API_LIST_DESTINATIONS` | List Destinations | Tool to retrieve all destinations configured on your RedCircle API account with pagination and filtering. Use when you need to browse or manage destination configurations. Returns 10 destinations per page. |
| `REDCIRCLE_API_LIST_ERROR_LOGS` | List Error Logs | Tool to list all error logs on your RedCircle API account. Use when you need to retrieve failed API request logs with error details. Results are paginated with 10 error logs per page. Supports filtering by search term and sorting by date or count. |
| `REDCIRCLE_API_LIST_REQUESTS_BY_PAGE` | List Requests by Page | Tool to retrieve requests for a collection in paginated format. Use when you need to access collection requests with pagination support (max 1000 requests per page). |
| `REDCIRCLE_API_LIST_RESULT_SETS` | List Result Sets | Tool to list all result sets for a collection. Use when you need to retrieve execution history and results for a specific collection. Note: result sets have 14-day retention. |
| `REDCIRCLE_API_LIST_ZIPCODES` | List Zipcodes | Tool to retrieve all zipcodes associated with your account with optional filtering. Use when you need to list zipcodes, optionally filtered by search term or domain. Supports pagination with max 10 results per page. |
| `REDCIRCLE_API_RESEND_WEBHOOK` | Resend Webhook | Tool to resend a previously configured webhook POST request for a result set. Use when you need to debug webhook connectivity issues without re-executing the collection. |
| `REDCIRCLE_API_START_COLLECTION` | Start Collection | Tool to initiate execution of a RedCircle API collection. Use when you need to start processing requests for a collection. Requires sufficient request credits and the collection must not be currently running. |
| `REDCIRCLE_API_STOP_ALL_COLLECTIONS` | Stop All Collections | Tool to halt all currently active collections on your account. Use when you need to terminate all collection operations across your account. Collections in queued or running states are affected, resetting status to idle. Note: Queued collections receive credit refunds; running collections stop without reimbursement. |
| `REDCIRCLE_API_STOP_COLLECTION` | Stop Collection | Tool to halt an active collection in queued or running state. Use when you need to stop a collection that is currently processing. Collections in queued status receive full credit refunds, while running collections are stopped without refunds. |
| `REDCIRCLE_API_UPDATE_COLLECTION` | Update Collection | Tool to update an existing collection's configuration and settings. Use when you need to modify collection settings including name, schedule, priority, and destination assignments. Note: A collection can only be updated when it is not running. |
| `REDCIRCLE_API_UPDATE_DESTINATION` | Update Destination | Tool to modify an existing destination configuration on your RedCircle API account. Use when you need to update destination settings such as name, credentials, storage paths, or enable/disable status. When enabling a previously disabled destination or updating credentials, a connectivity test will be performed automatically. |
| `REDCIRCLE_API_UPDATE_REQUEST` | Update Request | Tool to modify a request within a collection. Use only when the collection is not running. Updates request parameters like type, tcin, or other Target Product Data API fields. |

## Supported Triggers

None listed.

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

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

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

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 RedCircle API 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, redcircle api)
- 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 RedCircle API 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=["redcircle_api"],
    )

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

  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 RedCircle API 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 RedCircle API
```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 RedCircle API, 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=["redcircle_api"],
    )

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

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

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

## Related Toolkits

- [Addresszen](https://composio.dev/toolkits/addresszen) - Addresszen is a real-time address autocomplete and verification service. It helps capture accurate, deliverable addresses with instant suggestions and validation.
- [Asin data api](https://composio.dev/toolkits/asin_data_api) - Asin data api gives you detailed, real-time product data from Amazon, including price, rank, and reviews. Perfect for e-commerce pros and data-driven marketers who need instant marketplace insights.
- [Baselinker](https://composio.dev/toolkits/baselinker) - BaseLinker is an all-in-one e-commerce management platform connecting stores, marketplaces, carriers, and more. It streamlines order processing, inventory control, and automates your sales operations.
- [Bestbuy](https://composio.dev/toolkits/bestbuy) - Best Buy is a leading retailer offering APIs for product, store, and recommendation data. Instantly access up-to-date retail insights for smarter shopping and decision-making.
- [Btcpay server](https://composio.dev/toolkits/btcpay_server) - BTCPay Server is a free, open-source, self-hosted Bitcoin payment processor. It lets merchants accept Bitcoin payments directly, cutting out middlemen and boosting privacy.
- [Cdr platform](https://composio.dev/toolkits/cdr_platform) - Cdr platform is an API for purchasing carbon dioxide removal services. It enables businesses to offset emissions by accessing verified carbon removal projects.
- [Cloudcart](https://composio.dev/toolkits/cloudcart) - CloudCart is an e-commerce platform for building and managing online stores. It helps businesses streamline product listings, orders, and customer engagement.
- [Countdown api](https://composio.dev/toolkits/countdown_api) - Countdown API gives you real-time, structured eBay product data, reviews, and seller feedback. Perfect for powering price monitoring, product research, or marketplace analytics workflows.
- [Dpd2](https://composio.dev/toolkits/dpd2) - Dpd2 is a robust email management platform for handling, sorting, and automating email workflows. Streamline your communications and boost productivity with advanced sorting, labeling, and response tools.
- [Finerworks](https://composio.dev/toolkits/finerworks) - FinerWorks is an online platform for fine art and photo printing services. Artists and photographers use it to order custom prints and manage print inventory efficiently.
- [Fingertip](https://composio.dev/toolkits/fingertip) - Fingertip is a business management platform for selling, booking, and customer engagement—all from a single link. It helps businesses streamline operations and connect with customers across social channels.
- [Fraudlabs pro](https://composio.dev/toolkits/fraudlabs_pro) - FraudLabs Pro is an online payment fraud detection service for e-commerce and merchants. It helps minimize chargebacks and revenue loss by detecting and preventing fraudulent transactions.
- [Gift up](https://composio.dev/toolkits/gift_up) - Gift Up! is a digital platform for selling, managing, and redeeming gift cards online. It streamlines promotions and gift card transactions for businesses and their customers.
- [Goody](https://composio.dev/toolkits/goody) - Goody is a gifting platform that lets users send gifts and physical products without handling logistics. It streamlines gifting by managing delivery, fulfillment, and recipient experience.
- [Gumroad](https://composio.dev/toolkits/gumroad) - Gumroad is a platform for selling digital products, physical goods, and memberships with a simple checkout and marketing tools. It streamlines creator payouts and helps you grow your audience effortlessly.
- [Instacart](https://composio.dev/toolkits/instacart) - Instacart is an online grocery delivery and pickup service platform. It lets you discover local retailers and create shoppable lists and recipes with ease.
- [Junglescout](https://composio.dev/toolkits/junglescout) - Junglescout is an Amazon product research and analytics platform for sellers. It delivers sales estimates, competitive insights, and optimization tools to boost your Amazon business.
- [Ko fi](https://composio.dev/toolkits/ko_fi) - Ko-fi is a platform that lets creators receive donations, memberships, and sales from fans. It helps creators monetize their work and grow their audience with minimal friction.
- [Lemon squeezy](https://composio.dev/toolkits/lemon_squeezy) - Lemon Squeezy is a payments and subscription platform built for software companies. It makes managing payments, taxes, and customer subscriptions effortless.
- [Loyverse](https://composio.dev/toolkits/loyverse) - Loyverse is a point-of-sale (POS) platform for small businesses, offering tools for sales, inventory, and customer loyalty. It helps streamline retail operations and boost customer engagement.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and RedCircle API MCP?

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

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

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

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