How to integrate Fireworks AI MCP with LangChain

This guide walks you through connecting Fireworks AI to LangChain using the Composio tool router. By the end, you'll have a working Fireworks AI agent that can generate model responses, create chat completions, embed text, rerank documents, and list deployments through natural language commands. This guide will help you understand how to give your LangChain agent real control over a Fireworks AI account through Composio's Fireworks AI MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for free Get a demo

Fireworks AI

Api Key

Fireworks AI is a serverless AI platform for model inference, fine-tuning, deployments, datasets, and evaluations. Use it to run fast open-model workflows without managing GPU infrastructure.

9 Tools

Managed auth

Connect Fireworks AI without auth hassles

We manage OAuth, API keys, token refresh, and scopes — you just build.

Try for free

Introduction

This guide will help you understand how to give your LangChain agent real control over a Fireworks AI account through Composio's Fireworks AI MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Fireworks AI with

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenClaw Hermes CLI Google ADK Vercel AI SDK Mastra AI LlamaIndex CrewAI

TL;DR

Here's what you'll learn:

Get and set up your OpenAI and Composio API keys
Connect your Fireworks AI project to Composio
Create a Tool Router MCP session for Fireworks AI
Initialize an MCP client and retrieve Fireworks AI tools
Build a LangChain agent that can interact with Fireworks AI
Set up an interactive chat interface for testing

What is LangChain?

LangChain is a framework for developing applications powered by language models. It provides tools and abstractions for building agents that can reason, use tools, and maintain conversation context.

Key features include:

Agent Framework: Build agents that can use tools and make decisions
MCP Integration: Connect to external services through Model Context Protocol adapters
Memory Management: Maintain conversation history across interactions
Multi-Provider Support: Works with OpenAI, Anthropic, and other LLM providers

What is the Fireworks AI MCP server, and what's possible with it?

The Fireworks 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 Fireworks AI account. It provides structured and secure access to model inference, embeddings, reranking, models, deployments, and account information, so your agent can generate responses, create embeddings, rank documents, inspect models, and monitor deployments on your behalf.

Conversational model responses: Have your agent generate chat completions or other model responses from your prompts and role-based conversations.
Semantic embeddings: Instruct your agent to turn text into embedding vectors for search, clustering, recommendations, or similarity analysis.
Relevant document ranking: Let the agent rank a collection of documents against a query so the most useful results appear first.
Model discovery and inspection: Direct your agent to list available models and review the metadata and status of a specific model.
Account and deployment visibility: Have your agent find accessible accounts, list deployments, and inspect deployment configuration, serving capacity, and status.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step10 STEPS

Prerequisites

Before starting this tutorial, make sure you have:

Python 3.10 or higher installed on your system
A Composio account with an API key
An OpenAI API key
Basic familiarity with Python and async programming

Getting API Keys for OpenAI and Composio

OpenAI API Key

Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
Keep the API key safe.

Composio API Key

Log in to the Composio dashboard.
Navigate to your API settings and generate a new API key.
Store this key securely as you'll need it for authentication.

Install dependencies

npm install @composio/langchain @langchain/core @langchain/openai @langchain/mcp-adapters dotenv

Install the required packages for LangChain with MCP support.

What's happening:

@composio/langchain provides Composio integration for LangChain
@langchain/mcp-adapters enables MCP client connections
@langchain/core is the core agent framework
dotenv/config loads environment variables

Set up environment variables

bash

COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_composio_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

COMPOSIO_API_KEY authenticates your requests to Composio's API
COMPOSIO_USER_ID identifies the user for session management
OPENAI_API_KEY enables access to OpenAI's language models

Import dependencies

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

dotenv.config();

What's happening:

We're importing LangChain's MCP adapter and Composio SDK
The dotenv/config import loads environment variables from your .env file
This setup prepares the foundation for connecting LangChain with Fireworks AI functionality through MCP

Initialize Composio client

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.COMPOSIO_USER_ID;

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });

What's happening:

We're loading the COMPOSIO_API_KEY from environment variables and validating it exists
Creating a Composio instance that will manage our connection to Fireworks AI tools
Validating that COMPOSIO_USER_ID is also set before proceeding

Create a Tool Router session

const session = await composio.create(
    userId as string,
    {
        toolkits: ['fireworks_ai']
    }
);

const url = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Fireworks AI tools
The create method takes the user ID and specifies which toolkits should be available
The returned session.mcp.url is the MCP server URL that your agent will use
This approach allows the agent to dynamically load and use Fireworks AI tools as needed

Configure the agent with the MCP URL

const client = new MultiServerMCPClient({
    "fireworks_ai-agent": {
        transport: "http",
        url: url,
        headers: {
            "x-api-key": process.env.COMPOSIO_API_KEY
        }
    }
});

const tools = await client.getTools();

const agent = createAgent({ model: "gpt-5", tools });

What's happening:

We're creating a MultiServerMCPClient that connects to our Fireworks AI MCP server via HTTP
The client is configured with a name and the URL from our Tool Router session
getTools() retrieves all available Fireworks AI tools that the agent can use
We're creating a LangChain agent using the GPT-5 model

Set up interactive chat interface

let conversationHistory: any[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log("Ask any Fireworks AI related question or task to the agent.\n");

const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: '
});

rl.prompt();

rl.on('line', async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
        console.log("\nGoodbye!");
        rl.close();
        process.exit(0);
    }

    if (!trimmedInput) {
        rl.prompt();
        return;
    }

    conversationHistory.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    const response = await agent.invoke({ messages: conversationHistory });
    conversationHistory = response.messages;

    const finalResponse = response.messages[response.messages.length - 1]?.content;
    console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\n👋 Session ended.');
        process.exit(0);
    });

What's happening:

We initialize an empty conversationHistory list to maintain context across interactions
A readline interface is used to continuously accept user input from the command line
When a user types a message, it's added to the conversation history and sent to the agent
The agent processes the request using the invoke() method with the full conversation history
Users can type 'exit', 'quit', or 'bye' to end the chat session gracefully

Run the application

main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});

What's happening:

We call the main() function to start the application

Complete Code

Here's the complete code to get you started with Fireworks AI and LangChain:

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";  
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.COMPOSIO_USER_ID;

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });

    const session = await composio.create(
        userId as string,
        {
            toolkits: ['fireworks_ai']
        }
    );

    const url = session.mcp.url;
    
    const client = new MultiServerMCPClient({
        "fireworks_ai-agent": {
            transport: "http",
            url: url,
            headers: {
                "x-api-key": process.env.COMPOSIO_API_KEY
            }
        }
    });
    
    const tools = await client.getTools();
  
    const agent = createAgent({ model: "gpt-5", tools });
    
    let conversationHistory: any[] = [];
    
    console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
    console.log("Ask any Fireworks AI related question or task to the agent.\n");
    
    const rl = readline.createInterface({
        input: process.stdin,
        output: process.stdout,
        prompt: 'You: '
    });

    rl.prompt();

    rl.on('line', async (userInput: string) => {
        const trimmedInput = userInput.trim();
        
        if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
            console.log("\nGoodbye!");
            rl.close();
            process.exit(0);
        }
        
        if (!trimmedInput) {
            rl.prompt();
            return;
        }
        
        conversationHistory.push({ role: "user", content: trimmedInput });
        console.log("\nAgent is thinking...\n");
        
        const response = await agent.invoke({ messages: conversationHistory });
        conversationHistory = response.messages;
        
        const finalResponse = response.messages[response.messages.length - 1]?.content;
        console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\nSession ended.');
        process.exit(0);
    });
}

main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});

Conclusion

You've successfully built a LangChain agent that can interact with Fireworks AI through Composio's Tool Router.

Key features of this implementation:

Dynamic tool loading through Composio's Tool Router
Conversation history maintenance for context-aware responses
Async Python provides clean, efficient execution of agent workflows

You can extend this further by adding error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

TOOLS

Supported Tools

Every Fireworks AI action and event your agent gets out of the box.

Create Chat Completion

Generate one non-streaming OpenAI-compatible chat completion from role-based messages using a caller-supplied Fireworks model or deployment ID.

Create Embeddings

Create embedding vectors for one or more caller-provided inputs using a caller-supplied Fireworks embedding model.

Generate Model Response

Generate one non-streaming Responses API result, optionally continuing a stored response or using function, MCP, or SSE tools; storage is off by default.

Get Deployment

Return configuration and serving status for one Fireworks deployment without scaling or modifying it.

Get Model

Return metadata and status for one model resource in a Fireworks account; this does not test whether the model can serve inference.

List Accounts

Return one page of Fireworks accounts accessible to the API key so an agent can obtain account IDs for model and deployment discovery.

List Deployments

Return one page of deployment resources in a Fireworks account for deployment ID discovery and serving-capacity and status inspection.

List Models

Return one page of model resources in a Fireworks account for model-ID discovery and status inspection; availability for inference is not guaranteed.

Rerank Documents

Rank a provided document list by relevance to a query using an optional caller-supplied Fireworks reranker model.

FRAMEWORKS

How to build Fireworks AI MCP Agent with another framework

OpenAI Agents SDK

Use Fireworks AI MCP with OpenAI Agents SDK

Claude Agent SDK

Use Fireworks AI MCP with Claude Agent SDK

Claude Code

Use Fireworks AI MCP with Claude Code

Claude Cowork

Use Fireworks AI MCP with Claude Cowork

Codex

Use Fireworks AI MCP with Codex

OpenClaw

Use Fireworks AI MCP with OpenClaw

Hermes

Use Fireworks AI MCP with Hermes

CLI

Use Fireworks AI MCP with CLI

Google ADK

Use Fireworks AI MCP with Google ADK

Vercel AI SDK

Use Fireworks AI MCP with Vercel AI SDK

Mastra AI

Use Fireworks AI MCP with Mastra AI

LlamaIndex

Use Fireworks AI MCP with LlamaIndex

CrewAI

Use Fireworks AI MCP with CrewAI

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

AltTextLab

Api Key

AltTextLab is an AI service that generates accessible, SEO-aware alt text for images. It helps teams make image content easier to understand, index, and publish.

Apiframe

Api Key

Apiframe is an API platform for generating and managing AI images, videos, music, uploads, assets, jobs, and custom LoRAs. It gives developers one clean API for creative AI workflows without juggling multiple model providers.

Arize AX

Api Key

Arize AX is an AI engineering platform for tracing, evaluating, and improving AI applications. Use it to debug LLM behavior, compare experiments, and improve production AI quality.

AssemblyAI

Api Key

AssemblyAI is a speech-to-text and audio intelligence API for uploaded or hosted media. Use it to turn audio and video into accurate transcripts, summaries, and insights.

FAQ

Frequently asked questions

With a standalone Fireworks AI MCP server, the agents and LLMs can only access a fixed set of Fireworks AI tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Fireworks AI and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. LangChain 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 Fireworks AI tools.

Yes, absolutely. You can configure which Fireworks 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.

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 Fireworks AI data and credentials are handled as safely as possible.

Start with Fireworks AI.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Fireworks AI tool your agent needs.Free to start.

Start building

Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREE BOOK A DEMO

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati

Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya

Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave

CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu

Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola

Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche

Co-Founder, Ingram Technologies

How to integrate Fireworks AI MCP with LangChain

Connect Fireworks AI without auth hassles

Introduction

Also integrate Fireworks AI with

TL;DR

What is LangChain?

What is the Fireworks AI MCP server, and what's possible with it?

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install dependencies

Set up environment variables

Import dependencies

Initialize Composio client

Create a Tool Router session

Configure the agent with the MCP URL

Set up interactive chat interface

Run the application

Complete Code

Conclusion

Supported Tools

How to build Fireworks AI MCP Agent with another framework

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

OpenClaw

Hermes

CLI

Google ADK

Vercel AI SDK

Mastra AI

LlamaIndex

CrewAI

Explore Other Toolkits

AltTextLab

Apiframe

Arize AX

AssemblyAI

Frequently asked questions

What are the differences in Tool Router MCP and Fireworks AI MCP?+

Can I use Tool Router MCP with LangChain?+

Can I manage the permissions and scopes for Fireworks AI while using Tool Router?+

How safe is my data with Composio Tool Router?+

Start with Fireworks AI.It takes 30 seconds.

Teams ship real agents on Composio