Create powerful AI workflows by connecting multiple MCP servers including Dropbox, Firecrawl Web Search, OpenRouter for enhanced automation capabilities in Klavis AI.
Complete file management solution for Dropbox cloud storage. Upload, download, organize files and folders, manage sharing and collaboration, handle file versions, create file requests, and perform batch operations on your Dropbox files and folders
Advanced web crawling, scraping, and search capabilities powered by Firecrawl
Access to multiple AI models through a unified API. Generate chat completions, compare model performance, manage usage and costs, get model recommendations, and analyze model capabilities across various providers like OpenAI, Anthropic, Meta, Google, and more
Follow these steps to connect Fireworks AI to these MCP servers
Sign up for KlavisAI to access our MCP server management platform.
Add your desired MCP servers to Fireworks AI and configure authentication settings.
Verify your connections work correctly and start using your enhanced AI capabilities.
import os
import json
from fireworks.client import Fireworks
from klavis import Klavis
from klavis.types import McpServerName, ConnectionType, ToolFormat
# Initialize clients
fireworks_client = Fireworks(api_key=os.getenv("FIREWORKS_API_KEY"))
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))
dropbox_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.DROPBOX,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
firecrawl_web_search_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.FIRECRAWL_WEB_SEARCH,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
openrouter_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.OPENROUTER,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
# Get all MCP tools
dropbox_tools = klavis_client.mcp_server.list_tools(
server_url=dropbox_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.OPENAI,
)
firecrawl_web_search_tools = klavis_client.mcp_server.list_tools(
server_url=firecrawl_web_search_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.OPENAI,
)
openrouter_tools = klavis_client.mcp_server.list_tools(
server_url=openrouter_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.OPENAI,
)
# Combine all tools
all_tools = []
all_tools.extend(dropbox_tools.tools)
all_tools.extend(firecrawl_web_search_tools.tools)
all_tools.extend(openrouter_tools.tools)
messages = [
{"role": "system", "content": "You are a helpful assistant with access to multiple data sources."},
{"role": "user", "content": user_message}
]
response = fireworks_client.chat.completions.create(
model="accounts/fireworks/models/llama-v3p1-70b-instruct",
messages=messages,
tools=all_tools
)
Everything you need to know about connecting to these MCP servers
Join developers who are already using KlavisAI to power their Fireworks AI applications with these MCP servers.
Start For Free