# How to integrate Taxjar MCP with LlamaIndex

```json
{
  "title": "How to integrate Taxjar MCP with LlamaIndex",
  "toolkit": "Taxjar",
  "toolkit_slug": "taxjar",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/taxjar/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/taxjar/framework/llama-index.md",
  "updated_at": "2026-05-12T10:27:58.416Z"
}
```

## Introduction

This guide walks you through connecting Taxjar to LlamaIndex using the Composio tool router. By the end, you'll have a working Taxjar agent that can calculate sales tax for a new order, list all order transactions this month, show your current nexus regions through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Taxjar account through Composio's Taxjar MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Taxjar with

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

The Taxjar MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Taxjar account. It provides structured and secure access to your sales tax data, so your agent can perform actions like calculating sales tax, managing transactions, listing customers, and monitoring nexus regions on your behalf.
- Real-time tax calculation for orders: Instantly calculate accurate sales tax for new orders, factoring in nexus addresses, line items, shipping, and exemptions.
- Order and refund transaction management: Let your agent create, list, or delete order and refund transactions to streamline your sales and returns workflow.
- Customer database access: Effortlessly retrieve, list, or delete customer records for tax reporting and compliance purposes.
- Nexus region insights: Quickly identify and list all nexus regions where your business has sales tax obligations.
- Automated transaction reporting: Access up-to-date lists of transactions and refunds for reconciliation, filing, and audit readiness.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `TAXJAR_CALCULATE_SALES_TAX_FOR_AN_ORDER` | Calculate Sales Tax For An Order | Tool to calculate sales tax for an order. Use when you need an accurate tax calculation including nexus addresses, line items, shipping, and exemptions. |
| `TAXJAR_CREATE_CUSTOMER` | Create Customer | Tool to create a new customer with exemption information. Use when you need to add a customer to your TaxJar account for tax exemption management. |
| `TAXJAR_CREATE_ORDER_TRANSACTION` | Create Order Transaction | Creates a new order transaction in TaxJar for sales tax reporting and compliance. This action records order transactions that will appear in the TaxJar dashboard for tax filing purposes. The transaction includes customer location, order amounts, shipping costs, and sales tax collected. Important: The 'amount' field must include shipping but exclude sales tax. If line_items are provided, their sum (quantity * unit_price - discount) must equal amount minus shipping. |
| `TAXJAR_CREATE_REFUND_TRANSACTION` | Create Refund Transaction | Tool to create a new refund transaction. Use after confirming refund details. |
| `TAXJAR_DELETE_CUSTOMER` | Delete Customer | Tool to delete an existing customer. Use when you need to remove a previously created customer by its ID. Example: "Delete customer cust_12345". |
| `TAXJAR_DELETE_ORDER_TRANSACTION` | Delete Order Transaction | Tool to delete an existing order transaction. Use when you need to remove a previously created order transaction by its ID. Example: "Delete transaction abc123". |
| `TAXJAR_DELETE_REFUND_TRANSACTION` | Delete Refund Transaction | Tool to delete an existing refund transaction. Use when you need to remove a previously created refund transaction by its ID. Example: "Delete refund 243345". |
| `TAXJAR_LIST_CUSTOMERS` | List Customers | Lists all customer IDs from your TaxJar account. Returns a paginated list of customer IDs (strings). To get full details for a specific customer (including name, address, exemption type, etc.), use the customer ID with the 'Show Customer' action. Use this action to: - Browse all customers in your TaxJar account - Find customer IDs for further operations - Check which customers have been created |
| `TAXJAR_LIST_NEXUS_REGIONS` | List Nexus Regions | Tool to list existing nexus regions for an account. Use after authenticating your account to discover where you have nexus for sales tax purposes. |
| `TAXJAR_LIST_ORDER_TRANSACTIONS` | List Order Transactions | List order transaction IDs within a date range. Returns an array of transaction IDs (strings) for orders created between the specified dates. Use this to discover which orders exist in a date range, then use SHOW_ORDER_TRANSACTION to get details for specific IDs. |
| `TAXJAR_LIST_REFUND_TRANSACTIONS` | List refund transactions | Lists refund transaction IDs within a specified date range. Returns an array of transaction IDs only. To get detailed information about a specific refund, use the 'Show refund transaction' action with the ID. Useful for finding refunds created through the TaxJar API within a specific time period. |
| `TAXJAR_LIST_TAX_CATEGORIES` | List Tax Categories | Tool to list all product tax categories and their codes. Use when you need to discover available tax categories before assigning them to products. |
| `TAXJAR_SHOW_CUSTOMER` | Show Customer | Tool to show an existing customer. Use when you need to retrieve details of a specific customer via TaxJar API. |
| `TAXJAR_SHOW_ORDER_TRANSACTION` | Show Order Transaction | Tool to show an existing order transaction by ID. Use when you need to retrieve full details of a specific order transaction after creation or listing. |
| `TAXJAR_SHOW_REFUND_TRANSACTION` | Show Refund Transaction | Retrieves detailed information about a specific refund transaction from TaxJar. Use this tool when you need to: - View complete details of a refund transaction including amounts, addresses, and line items - Verify refund transaction data that was previously created - Audit refund information for tax reporting purposes Requires a valid transaction_id that was previously created through TaxJar's API. |
| `TAXJAR_SHOW_TAX_RATES_FOR_A_LOCATION` | Show Tax Rates for a Location | Tool to show sales tax rates for a location. Use when you need to retrieve sales tax rates for a specific ZIP code with optional address details (city, state, country, street). |
| `TAXJAR_SUMMARIZE_TAX_RATES_FOR_ALL_REGIONS` | Summarize Tax Rates for All Regions | Tool to retrieve minimum and average sales tax rates by region. Use when you need a backup of regional tax summary rates. |
| `TAXJAR_UPDATE_CUSTOMER` | Update Customer | Tool to update an existing customer in TaxJar. Use when you need to modify customer details such as exemption type, name, or address information. |
| `TAXJAR_UPDATE_ORDER_TRANSACTION` | Update Order Transaction | Tool to update an existing order transaction. Use when adjusting order details such as amount, shipping, or line items after creation. |
| `TAXJAR_UPDATE_REFUND_TRANSACTION` | Update Refund Transaction | Tool to update an existing refund transaction. Use when adjusting refund details such as amount, shipping, or line items after creation. |
| `TAXJAR_VALIDATE_VAT_NUMBER` | Validate VAT Number | Validates EU VAT identification numbers against the VIES (VAT Information Exchange System) database. Use this tool to: - Verify VAT number format and validity - Check if a VAT number is registered and active in the EU - Retrieve associated company name and address when available - Confirm tax-exempt eligibility before processing transactions The validation queries the European VIES database when available, returning company details for valid registrations. When VIES is unavailable, it falls back to format-based validation using regex patterns. |

## Supported Triggers

None listed.

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

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

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

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 Taxjar 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, taxjar)
- 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 Taxjar 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=["taxjar"],
    )

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

  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 Taxjar 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 Taxjar
```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 Taxjar, 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=["taxjar"],
    )

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

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

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

## Related Toolkits

- [Stripe](https://composio.dev/toolkits/stripe) - Stripe is a global online payments platform offering APIs for managing payments, customers, and subscriptions. Trusted by businesses for secure, efficient, and scalable payment processing worldwide.
- [Alpha vantage](https://composio.dev/toolkits/alpha_vantage) - Alpha Vantage is a financial data platform offering real-time and historical stock market APIs. Get instant, reliable access to equities, forex, and technical analysis data for smarter trading decisions.
- [Altoviz](https://composio.dev/toolkits/altoviz) - Altoviz is a cloud-based billing and invoicing platform for businesses. It streamlines online payments, expense tracking, and customizable invoice management.
- [Benzinga](https://composio.dev/toolkits/benzinga) - Benzinga provides real-time financial news and data APIs for market coverage. It helps you track breaking news and actionable market insights instantly.
- [Brex](https://composio.dev/toolkits/brex) - Brex provides corporate credit cards and spend management tailored for startups and tech businesses. It helps optimize company cash flow, streamline accounting, and accelerate business growth.
- [Chaser](https://composio.dev/toolkits/chaser) - Chaser is accounts receivable automation software that sends invoice reminders and helps businesses get paid faster. It streamlines the collections process to save time and improve cash flow.
- [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.
- [Coinbase](https://composio.dev/toolkits/coinbase) - Coinbase is a platform for buying, selling, and storing cryptocurrency. It makes exchanging and managing crypto simple and secure for everyone.
- [Coinranking](https://composio.dev/toolkits/coinranking) - Coinranking is a comprehensive cryptocurrency market data platform offering access to real-time coin prices, market caps, and historical data. Get accurate, up-to-date stats for thousands of digital assets in one place.
- [Coupa](https://composio.dev/toolkits/coupa) - Coupa is a business spend management platform for procurement, invoicing, and expenses. It helps organizations streamline purchasing, control costs, and gain complete visibility over financial operations.
- [CurrencyScoop](https://composio.dev/toolkits/currencyscoop) - CurrencyScoop is a developer-friendly API for real-time and historical currency exchange rates. Easily access fiat and crypto data for smart, up-to-date financial applications.
- [Daffy](https://composio.dev/toolkits/daffy) - Daffy is a modern charitable giving platform with a donor-advised fund. Easily set aside funds, grow them tax-free, and donate to over 1.7 million U.S. charities.
- [Eagle doc](https://composio.dev/toolkits/eagle_doc) - Eagle doc is an AI-powered OCR API for invoices and receipts. It delivers fast, reliable, and accurate document data extraction for seamless automation.
- [Elorus](https://composio.dev/toolkits/elorus) - Elorus is an online invoicing and time-tracking software for freelancers and small businesses. Easily manage finances, bill clients, and track work in one place.
- [Eodhd apis](https://composio.dev/toolkits/eodhd_apis) - Eodhd apis delivers comprehensive financial data, including live and historical stock prices, via robust APIs. Easily access reliable, up-to-date market insights to power your apps, dashboards, and analytics.
- [Fidel api](https://composio.dev/toolkits/fidel_api) - Fidel api is a secure platform for linking payment cards to web and mobile apps. It enables real-time card transaction monitoring and event-based automation for businesses.
- [Finage](https://composio.dev/toolkits/finage) - Finage is a secure API platform delivering real-time and historical financial data for stocks, forex, crypto, indices, and commodities. It empowers developers and businesses to access, analyze, and act on market data instantly.
- [Finmei](https://composio.dev/toolkits/finmei) - Finmei is an invoicing tool that simplifies billing, invoice management, and expense tracking. Ideal for automating and organizing your business finances in one place.
- [Fixer](https://composio.dev/toolkits/fixer) - Fixer is a currency data API offering real-time and historical exchange rates for 170 currencies. Instantly access accurate, up-to-date forex data for your applications and workflows.
- [Fixer io](https://composio.dev/toolkits/fixer_io) - Fixer.io is a lightweight API for real-time and historical foreign exchange rates. It makes global currency conversion fast, accurate, and hassle-free.

## Frequently Asked Questions

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

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

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

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

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