Create powerful AI workflows by connecting multiple MCP servers including Markdown2doc, Dropbox, Hacker News with Claude's advanced reasoning capabilities in Klavis AI.
Convert markdown text to different file formats (pdf, docx, doc, html), based on Pandoc
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
Access the latest tech news, discussions, and stories from Hacker News. Fetch top stories, newest posts, best stories, show HN posts, ask HN posts, job listings, and user profiles from the popular tech community platform
Follow these steps to connect Claude to these MCP servers
Sign up for KlavisAI to access our MCP server management platform and get your API keys.
Add your desired MCP servers to Claude and configure authentication settings with your Anthropic API key.
Verify your connections work correctly with Claude's function calling and start using your enhanced AI capabilities.
import os
import json
from anthropic import Anthropic
from klavis import Klavis
from klavis.types import McpServerName, ConnectionType, ToolFormat
# Initialize clients
anthropic_client = Anthropic(api_key=os.getenv("ANTHROPIC_API_KEY"))
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))
# Constants
CLAUDE_MODEL = "claude-3-5-sonnet-20241022"
user_message = "Your message here"
markdown2doc_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.MARKDOWN2DOC,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
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,
)
hacker_news_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.HACKER_NEWS,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
# Get tools from all MCP servers
markdown2doc_tools = klavis_client.mcp_server.list_tools(
server_url=markdown2doc_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.ANTHROPIC,
)
dropbox_tools = klavis_client.mcp_server.list_tools(
server_url=dropbox_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.ANTHROPIC,
)
hacker_news_tools = klavis_client.mcp_server.list_tools(
server_url=hacker_news_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.ANTHROPIC,
)
# Combine all tools
all_tools = []
all_tools.extend(markdown2doc_tools.tools)
all_tools.extend(dropbox_tools.tools)
all_tools.extend(hacker_news_tools.tools)
messages = [
{"role": "user", "content": user_message}
]
response = anthropic_client.messages.create(
model=CLAUDE_MODEL,
max_tokens=4000,
messages=messages,
tools=all_tools
)
Everything you need to know about connecting Claude to these MCP servers
Join developers who are already using KlavisAI to power their Claude applications with these MCP servers.
Start For Free