# How to integrate Mistral ai MCP with LlamaIndex

```json
{
  "title": "How to integrate Mistral ai MCP with LlamaIndex",
  "toolkit": "Mistral ai",
  "toolkit_slug": "mistral_ai",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/mistral_ai/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/mistral_ai/framework/llama-index.md",
  "updated_at": "2026-05-12T10:19:10.140Z"
}
```

## Introduction

This guide walks you through connecting Mistral ai to LlamaIndex using the Composio tool router. By the end, you'll have a working Mistral ai agent that can summarize this research paper in simple terms, generate python code for sorting a list, explain the difference between ai and ml through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Mistral ai account through Composio's Mistral ai MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Mistral ai with

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

The Mistral ai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mistral ai account. It provides structured and secure access to your Mistral AI models, so your agent can perform actions like generating text, summarizing content, answering questions, extracting structured information, and handling advanced language tasks on your behalf.
- Text generation and completion: Have your agent produce coherent, context-aware text responses, complete prompts, or generate creative content leveraging Mistral's advanced models.
- Summarization and paraphrasing: Ask your agent to summarize lengthy documents or rephrase input text for improved clarity or brevity.
- Question answering and information extraction: Let your agent answer questions, extract key facts, or pull structured data from unstructured content automatically.
- Content classification and sentiment analysis: Enable your agent to categorize text, detect topics, or analyze sentiment to inform downstream workflows.
- Conversational AI and dialogue management: Build rich, multi-turn conversations or chatbots that handle context, intent, and user queries seamlessly using Mistral's models.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `MISTRAL_AI_APPEND_TO_CONVERSATION` | Append to conversation | Tool to append new entries to an existing conversation in Mistral AI. Use when you need to continue a conversation by adding new messages or inputs. This is a beta endpoint. |
| `MISTRAL_AI_CREATE_AGENT` | Create Agent | Tool to create a new AI agent with custom configuration (Beta). Use when you need to create an agent with specific model, name, instructions, and tools. |
| `MISTRAL_AI_CREATE_AGENTS_COMPLETION` | Create Agents Completion | Tool to generate completions using a Mistral AI agent with specific instructions and tools. Use when you need an agent to process messages and generate responses. Agents can use tools, follow instructions, and maintain conversation context. |
| `MISTRAL_AI_CREATE_AUDIO_TRANSCRIPTION` | Create Audio Transcription | Transcribe audio files to text using Mistral AI's Voxtral models. Use this action to convert speech in audio files to written text. Supports multiple input methods: file upload, file_id from previously uploaded files, or file_url for publicly accessible audio. The transcription supports 13 languages with automatic language detection, speaker diarization, and configurable timestamp granularities (segment or word level). Key features: - Multi-language support (English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, Dutch) - Speaker diarization to identify different speakers - Word and segment-level timestamps - Context biasing for domain-specific terminology - Supports common audio formats (mp3, wav, m4a, etc.) Note: Exactly one of file, file_id, or file_url must be provided. The action does not support streaming mode. |
| `MISTRAL_AI_CREATE_CHAT_COMPLETION` | Create Chat Completion | Generate conversational responses from Mistral AI models. Supports streaming, function calling, and various model parameters. Use when you need to create chat completions with Mistral AI models for conversation, question answering, or function calling scenarios. |
| `MISTRAL_AI_CREATE_CHAT_MODERATION` | Create Chat Moderation | Tool to classify chat content for moderation purposes across 9 categories. Use when you need to detect harmful content, inappropriate messages, or policy violations in chat conversations. |
| `MISTRAL_AI_CREATE_EMBEDDINGS` | Create Embeddings | Tool to generate vector embeddings for input text using Mistral AI embedding models. Use when you need to convert text into numerical vectors for semantic search, similarity comparison, or RAG applications. |
| `MISTRAL_AI_CREATE_FIM_COMPLETION` | Create FIM Completion | Generate code completions using fill-in-the-middle functionality. Use when you need to complete code between a prefix and suffix, or continue code from a prompt. Ideal for code completion, function implementation, and context-aware code generation. |
| `MISTRAL_AI_CREATE_LIBRARY` | Create library | Tool to create a new document library. Use when you need to group documents into a new library. Use after confirming authentication. |
| `MISTRAL_AI_CREATE_LIBRARY_SHARE` | Create library share | Create or update sharing permissions for a library. Use to grant access to users, workspaces, or organizations. Specify the access level (Viewer or Editor) and the entity to share with. This is a beta endpoint. |
| `MISTRAL_AI_CREATE_MODERATION` | Create Moderation | Tool to classify text content for moderation purposes across 9 categories. Use when you need to detect harmful content, inappropriate text, or policy violations in raw text inputs. |
| `MISTRAL_AI_CREATE_OCR` | Create OCR | Extract text and structured data from images and documents using Mistral AI's OCR capabilities. Supports PDFs, images, tables, headers, footers, and custom structured extraction. Use when you need to digitize documents, extract invoice data, parse forms, or convert scanned documents to text. |
| `MISTRAL_AI_CREATE_OR_UPDATE_AGENT_ALIAS` | Create or Update Agent Alias | Tool to create or update an agent version alias. Use when you need to assign a version alias (like 'production' or 'staging') to a specific agent version. |
| `MISTRAL_AI_DELETE_AGENT` | Delete agent | Permanently deletes an agent by its ID (Beta feature). Use this tool when you need to remove an agent that is no longer needed. This operation is irreversible - the agent will be permanently removed from the system. |
| `MISTRAL_AI_DELETE_CONVERSATION` | Delete Conversation | Tool to delete a conversation by its ID (Beta). Use when you need to permanently remove a conversation. This is a beta feature. |
| `MISTRAL_AI_DELETE_FILE` | Delete File | Delete a file by its ID from Mistral AI. Permanently removes the file and its metadata. Use List Files action first to obtain valid file IDs. |
| `MISTRAL_AI_DELETE_LIBRARY` | Delete library | Permanently deletes a library and all of its documents from Mistral AI. Use this tool when you need to remove an entire library including all its documents. This operation is irreversible - the library and all its documents will be permanently removed. Returns the deleted library details on success. Common errors: - 404: Library not found (already deleted or invalid library_id) - 422: Invalid UUID format for library_id |
| `MISTRAL_AI_DELETE_LIBRARY_DOCUMENT` | Delete library document | Permanently deletes a document from a Mistral AI library. Use this tool when you need to remove a specific document from a library. Both library_id and document_id must be valid UUIDs. This operation is irreversible - the document will be permanently removed. Returns an empty response on success (HTTP 204). Common errors: - 404: Document not found (already deleted or invalid document_id) - 422: Invalid UUID format for library_id or document_id |
| `MISTRAL_AI_DELETE_LIBRARY_SHARE` | Delete library share | Remove sharing permissions for a library from a user, workspace, or organization. Use when you need to revoke access to a library that was previously shared. This is a beta feature. |
| `MISTRAL_AI_DOWNLOAD_FILE` | Download File | Download the content of a previously uploaded file from Mistral AI. Returns the raw binary content of the file. Use this when you need to retrieve file data for processing, such as training data files (.jsonl) for fine-tuning. Requires a valid file_id which can be obtained from the list_files or upload_file actions. |
| `MISTRAL_AI_GET_AGENT` | Get Agent | Tool to retrieve details of a specific Mistral AI agent by its ID. Returns comprehensive agent information including model, instructions, tools, and configuration. Use when you need to inspect or verify an agent's settings. |
| `MISTRAL_AI_GET_AGENT_VERSION` | Get Agent Version | Retrieve a specific version of an agent (Beta). Use when you need to get details about a particular agent version, including its configuration, tools, and metadata. |
| `MISTRAL_AI_GET_CONVERSATION` | Get Conversation | Tool to retrieve details of a specific conversation. Use when you need to fetch conversation metadata including timestamps, configuration, and associated model or agent information. |
| `MISTRAL_AI_GET_CONVERSATION_HISTORY` | Get Conversation History | Retrieve the full history of a conversation in Mistral AI. Returns all entries including messages, tool calls, function results, and agent handoffs. Use this to review conversation context or export conversation data. Note: This is a beta endpoint. |
| `MISTRAL_AI_GET_CONVERSATION_MESSAGES` | Get Conversation Messages | Retrieve all messages from a Mistral AI conversation. Use when you need to fetch the complete message history for a specific conversation. |
| `MISTRAL_AI_GET_DOCUMENT_EXTRACTED_TEXT_URL` | Get document extracted text URL | Retrieve a signed URL to download the extracted text from a document in a Mistral AI library. This is a beta endpoint. Note: Only documents that undergo OCR processing (such as PDFs) will have extracted text available; plain text files that don't require OCR will return a 404 error. |
| `MISTRAL_AI_GET_DOCUMENT_SIGNED_URL` | Get document signed URL | Get a signed URL to download a document from a Mistral AI library. Returns a temporary URL that provides direct access to download the document content. Use this when you need to retrieve document files from a library. The signed URL is typically valid for 30 minutes. |
| `MISTRAL_AI_GET_DOCUMENT_STATUS` | Get Document Status | Retrieve the processing status of a document in a Mistral AI library. Use this to check if a document has finished processing after upload. Returns the document ID and its current processing status. |
| `MISTRAL_AI_GET_DOCUMENT_TEXT_CONTENT` | Get Document Text Content | Retrieve the extracted text content of a specific document from a Mistral AI library (Beta). Returns the full text content extracted from the document. Use the List Libraries action first to obtain valid library IDs, then use List Library Documents to get document IDs. |
| `MISTRAL_AI_GET_FILE_SIGNED_URL` | Get File Signed URL | Get a time-limited signed URL for downloading a file from Mistral AI. Use when you need a temporary download link that can be shared or used externally. The URL expires after the specified number of hours (default 24). |
| `MISTRAL_AI_GET_FINE_TUNING_JOBS` | List Fine Tuning Jobs | List fine-tuning jobs with optional filtering and pagination. Use this tool to retrieve all fine-tuning jobs for your organization. Supports filtering by model, status, creation time, and W&B integration. Results are paginated; use 'page' and 'page_size' to navigate large result sets. |
| `MISTRAL_AI_GET_LIBRARY` | Get library | Retrieve detailed information about a specific library. Returns complete library metadata including name, description, document counts, size, timestamps, and ownership details. Use List Libraries action first to obtain valid library IDs. |
| `MISTRAL_AI_GET_LIBRARY_DOCUMENT` | Get Library Document | Retrieve metadata for a specific document in a Mistral AI library. Returns detailed information including processing status, size, summary, token counts, and timestamps. Use this to check document status after upload or to retrieve details for a known document. |
| `MISTRAL_AI_GET_MODEL` | Get Model | Tool to retrieve detailed information about a specific Mistral AI model by its ID. Returns model metadata including capabilities, context length, and ownership. Use when you need to inspect model specifications before using it. |
| `MISTRAL_AI_LIST_AGENT_ALIASES` | List agent aliases | Retrieve all aliases for an agent version. Use to view and manage version aliases for an agent. Note: This is a beta endpoint. |
| `MISTRAL_AI_LIST_AGENTS` | List Agents | Tool to list all configured agents (Beta). Use when you need to retrieve a list of agents available in your organization. |
| `MISTRAL_AI_LIST_AGENT_VERSIONS` | List Agent Versions | List all versions of a specific agent. Use when you need to view the version history of an agent. Note: This is a beta endpoint. |
| `MISTRAL_AI_LIST_BATCH_JOBS` | List Batch Jobs | Tool to retrieve a list of all batch jobs with optional filtering and pagination. Use when you need to view or manage batch processing jobs. |
| `MISTRAL_AI_LIST_CONVERSATIONS` | List Conversations | List all created conversations (Beta). Use to retrieve conversation history or manage existing conversations. Supports pagination and metadata filtering. |
| `MISTRAL_AI_LIST_FILES` | List Files | Tool to list all files available to the user. Use when you need to view or manage uploaded files, supports pagination. |
| `MISTRAL_AI_LIST_LIBRARIES` | List libraries | List all document libraries accessible to your organization. Returns library metadata including id, name, description, document counts, and timestamps. Use to discover available libraries before listing or uploading documents. Note: This is a beta endpoint. |
| `MISTRAL_AI_LIST_LIBRARY_DOCUMENTS` | List Library Documents | List all documents in a Mistral AI document library. Returns document metadata including name, processing status, size, summary, and timestamps. Use the List Libraries action first to obtain valid library IDs. Supports pagination for large libraries. |
| `MISTRAL_AI_LIST_LIBRARY_SHARES` | List library shares | List all sharing permissions for a document library. Returns details about who has access to the library, including role, share type, and user/organization identifiers. Use the List Libraries action first to obtain valid library IDs. Note: This is a beta endpoint. |
| `MISTRAL_AI_LIST_MODELS` | List Models | Tool to retrieve all available Mistral AI models including base models and fine-tuned models. Use when you need to see what models are available for chat completions, embeddings, or fine-tuning. |
| `MISTRAL_AI_REPROCESS_DOCUMENT` | Reprocess document | Reprocess a document in a Mistral AI library (Beta). Use when you need to trigger reprocessing of a document, such as after updating library settings or to refresh document embeddings. Both library_id and document_id must be valid UUIDs. Returns an empty response on success (HTTP 204). |
| `MISTRAL_AI_RESTART_CONVERSATION` | Restart Conversation | Tool to restart a conversation from a specific point (Beta). Use when you need to branch a conversation or replay it from a particular message. Creates a new conversation starting from the specified entry. |
| `MISTRAL_AI_RETRIEVE_FILE` | Retrieve File | Retrieve metadata of a file uploaded to Mistral AI. Returns file details including size, filename, purpose, and creation time. Use List Files action first to obtain valid file IDs. |
| `MISTRAL_AI_START_CONVERSATION` | Start Conversation | Tool to start a new conversation with a Mistral AI agent or base model. Use when initiating a conversational interaction that requires context tracking. Either 'model' or 'agent_id' must be provided. Returns a conversation_id for continuing the conversation. |
| `MISTRAL_AI_UPDATE_AGENT` | Update Agent | Tool to update an existing agent's configuration. Use when you need to modify an agent's name, description, model, instructions, tools, or other settings. |
| `MISTRAL_AI_UPDATE_AGENT_VERSION` | Update agent version | Tool to update the current version of an agent (Beta). Use when you need to switch an agent to a different version from its available versions. |
| `MISTRAL_AI_UPDATE_LIBRARY` | Update library | Tool to update an existing document library's properties. Use when you need to modify a library's name or description. Note: This is a beta endpoint. |
| `MISTRAL_AI_UPDATE_LIBRARY_DOCUMENT` | Update library document | Update the metadata of a document in a Mistral AI library. Use this to modify a document's name or add/update custom attributes without re-uploading the file content. This is a beta endpoint. |
| `MISTRAL_AI_UPLOAD_FILE` | Upload File | Upload a file to Mistral AI for use in fine-tuning, batch processing, or OCR. Use this tool to: - Upload .jsonl files for fine-tuning models - Upload files for batch processing requests - Upload documents for OCR processing Maximum file size: 512 MB. For fine-tuning, only .jsonl files are supported. |
| `MISTRAL_AI_UPLOAD_LIBRARY_DOCUMENT` | Upload Library Document | Upload a document to a Mistral AI library for use with RAG-enabled agents. Use this action to add documents to a library that can be accessed by Mistral AI agents. The uploaded document will be processed and indexed for retrieval-augmented generation. Prerequisites: - First obtain a valid library_id using MISTRAL_AI_LIST_LIBRARIES or MISTRAL_AI_CREATE_LIBRARY. - Supported file formats include PDF, TXT, DOC, DOCX, and other common document types. - Maximum file size is 100 MB per document. |

## Supported Triggers

None listed.

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

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

### 1. Getting API Keys for OpenAI, Composio, and Mistral ai

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 Mistral ai 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, mistral ai)
- 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 Mistral ai 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=["mistral_ai"],
    )

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

  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 Mistral ai 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 Mistral ai
```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 Mistral ai, 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=["mistral_ai"],
    )

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

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

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

## Related Toolkits

- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.
- [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.
- [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.
- [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.
- [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application.
- [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities.
- [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization.
- [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications.
- [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations.
- [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key.
- [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient.
- [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions.
- [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences.
- [Chatbotkit](https://composio.dev/toolkits/chatbotkit) - Chatbotkit is a platform for building and managing AI-powered chatbots using robust APIs and SDKs. It lets you easily add conversational AI to your apps for better user engagement.
- [Cody](https://composio.dev/toolkits/cody) - Cody is an AI assistant built for businesses, trained on your company's knowledge and data. It delivers instant answers and insights, tailored for your team.
- [Context7 MCP](https://composio.dev/toolkits/context7_mcp) - Context7 MCP delivers live, version-specific code docs and examples right from the source. It helps developers and AI agents instantly retrieve authoritative programming info—no more out-of-date docs.
- [Customgpt](https://composio.dev/toolkits/customgpt) - CustomGPT.ai lets you build and deploy chatbots tailored to your own data and business needs. Get precise and context-aware AI conversations without writing code.
- [Datarobot](https://composio.dev/toolkits/datarobot) - Datarobot is a machine learning platform that automates model development, deployment, and monitoring. It empowers organizations to quickly gain predictive insights from large datasets.
- [Deepgram](https://composio.dev/toolkits/deepgram) - Deepgram is an AI-powered speech recognition platform for accurate audio transcription and understanding. It enables fast, scalable speech-to-text with advanced audio intelligence features.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Mistral ai MCP?

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

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

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

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